机器学习学术速递[8.12]

AI 总结：ChronoSSM是一种自回归状态空间模型，通过联合建模事件与时间戳的共享主干，在四个领域的实验中，能生成更具时间信息的表示且不降低内容生成质量。

链接：https://arxiv.org/abs/2608.10120

机构：ENS de Lyon（里昂高等师范学院）； CNRS（法国国家科学研究中心）； UCBL1（里昂第一大学）； Indian Institute of Technology Bombay（印度理工学院孟买分校）； Institut universitaire de France（法国大学研究院）

作者：Adrien Schoen, Nachiketa Ratnakar Patil, Arjun Bhagoji, Francesco Bronzino

英文摘要：Modern sequence models, from Transformers to State Space Models, have enabled powerful generative modeling across diverse domains, yet they are typically trained to predict what happens while treating when it happens as a secondary concern. In data-mining settings where events are associated with explicit timing information, this separation can limit temporal reasoning, anomaly detection, and faithful reconstruction of event chronology. A common strategy is to treat timing as an auxiliary signal, training a separate timing model using representations learned solely for event prediction. However, this two-stage approach implicitly assumes that representations optimized for event prediction already contain sufficient temporal structure. We introduce ChronoSSM, an autoregressive State Space Model (SSM) that jointly models events and timestamps with a shared backbone trained using combined token and temporal generation objectives. We compare the joint regime, where temporal supervision updates the backbone, with the two-stage regime, where timing is learned only using the frozen event representations. Across four domains spanning dense and partial timestamp supervision, joint training consistently makes inter-arrival information more recoverable from frozen representations without any systematic degradation in content-generation quality overall. Our results show that temporal supervision can produce more temporally informative representations without materially degrading autoregressive event modeling.

AI 总结：针对现有事后不确定性校准方法的缺陷，提出可逆对数变换InvLT，通过共享标量MLP实现参数不随类别数增长，在保留分类准确率的同时提升校准性能。

链接：https://arxiv.org/abs/2608.10372

机构：University of Pennsylvania（宾夕法尼亚大学）

作者：Lening Zhao, Qipeng Zhan, Li Shen

英文摘要：Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining. An ideal calibrator should correct nonlinear miscalibration, scale gracefully to large label spaces, and preserve the original predictions; existing methods typically violate at least one of these properties---temperature scaling lacks expressivity, more flexible parametric alternatives introduce parameters that grow with the number of classes $C$, and other expressive methods do not preserve the rank ordering of class scores and may alter the predicted class. We propose \textbf{Invertible Logits Transformation (InvLT)}, which applies a learned scalar MLP $f:\mathbb{R}\to\mathbb{R}$ element-wise to the pre-softmax logits. Sharing $f$ across all logit dimensions makes the parameter count independent of $C$. Monotonicity of $f$---and hence preservation of the argmax prediction---is softly encouraged via a paired inverse network rather than enforced through the numerical integration required by prior monotone calibrators; this avoids their computational overhead while empirically preserving the original classification accuracy in every setting we evaluate. Across standard image classification benchmarks and a range of architectures, InvLT consistently outperforms a broad set of post-hoc baselines on standard calibration metrics.

AI 总结：该研究针对MoE模型决策间的依赖问题，提出UniF-MoE统一框架，先共享再路由剩余部分，在DomainBed和GLUE实验中提升性能并降低计算资源消耗。

链接：https://arxiv.org/abs/2608.10392

作者： Gongli Zhang, Zhulin Liu, C. L. Philip Chen

英文摘要：Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts. Shared-expert designs preserve reusable knowledge, fine-grained methods vary computation within experts, and dynamic routers adapt the number of active experts. Yet these decisions are usually made independently, overlooking a basic dependency: extracting reusable computation changes both what remains and how much expert capacity the remainder needs. We study this dependency by decomposing sparsely upcycled feed-forward experts into key-value channels. Co-activated experts align at a subset of value positions; removing these positions changes expert preference; and greater shared coverage is associated with lower residual expert demand. These observations lead to one principle: share first, then route what remains. We instantiate it in UniF-MoE, a unified framework for token-adaptive MoE computation. Each expert is partitioned into aligned blocks. A shared-demand score sets the shared block count and pathway weight, key prototypes select the shared content, and the complementary demand determines the residual expert count through cumulative routing mass. A Gram regularizer separates and normalizes router embeddings, promoting diverse routing directions, sparse expert overlap, and a simple routing geometry. Experiments on DomainBed and GLUE show that this unified design improves predictive performance over representative static and dynamic MoEs while reducing activated computation, inference latency, and memory. Code is available at this https URL.

AI 总结：本研究开发MOSAIC框架，将稀疏MoE模型的架构与系统协同设计建模为优化问题，发现计算最优与集群最优稀疏性存在差异，主张统一架构与系统协同设计。

链接：https://arxiv.org/abs/2608.10605

机构：Amazon AGI Foundations（亚马逊AGI基础研究部门）

作者：Soumajyoti Sarkar, Yuxin Tang, Sheng Zha

英文摘要：In large-scale pretraining, the algorithm, architecture, and systems decisions are conventionally made in disconnected stages. A scaling law stage selects an architecture and training recipe, optimizing loss under compute constraints, and a separate systems stage then optimizes the implementation for hardware efficiency. In this work, we develop MOSAIC, which formulates model architecture and systems co-design as an optimization problem. MOSAIC couples a predictive scaling law with a calibrated performance model that estimates Model FLOPs Utilization (MFU), communication cost, memory footprint, and the best parallel layout. We instantiate the framework for sparse Mixture-of-Experts (MoE) language models, where expert count, routing sparsity, and other MoE layer dimensions affect both the loss and systems efficiency. We fit a scaling law on sparse MoE models trained on text data, whose scaling dimensions include the sparsity factor, which is the fraction of model parameters inactive per token in a forward pass. The scaling law sweeps in our work span active parameters from $104$ million to $2.7$ billion and total model sizes reaching $79$ billion parameters. We show that, within the calibrated sparsity range, an efficiency-agnostic model-FLOPs budget admits no interior optimal sparsity. The fitted loss decreases monotonically with sparser models and the compute optimum lies at the upper boundary of the data support. An optimal sparsity in MoE models instead emerges under the cluster's systems constraints, as captured by MOSAIC. Our results argue for a shift towards unified architecture and systems co-design for frontier language model training.

AI 总结：本文针对LLM RL后训练中故障复现成本高的问题，提出一种MoE代理模型构建方法，通过专家剪枝降低计算需求，可低成本复现故障并辅助诊断。

链接：https://arxiv.org/abs/2608.10823

作者：Yikai Wang, Chuansai Zhou, Yuhang Zhou, Weiqiang Wu, Cong Wu, Yue Deng, Ben Feng, Mingming Zhu, Beirong Zhou, Zhibin Wang, Sheng Zhong, Chen Tian, Wangze Zhang

英文摘要：Reinforcement learning (RL) post-training of large language models (LLMs) is computationally intensive and involves complex system pipelines with substantial debugging overhead. In practice, factors such as framework adaptation, numerical precision, and operator implementation can cause failures, including gradient overflow and loss divergence. Reproducing such failures directly on large models requires considerable time and computational resources. This paper systematically analyzes failures encountered during large-scale RL training on the Huawei Ascend platform, summarizes representative failure types, and identifies three model-side factors relevant to fault reproduction. Based on these factors, we propose a proxy-model construction method for low-cost fault investigation and auxiliary diagnosis. It employs structure-preserving, clustering-based expert pruning to select representative experts while retaining the model's backbone architecture, routing mechanism, and basic task capabilities. Our experimental results show that the proxy models reduce accelerator requirements by 50%-87.5% and achieve up to a 33.3x reduction in per-step NPU-hour cost, while preserving major training dynamics and reproducing fault responses consistent with the original models. Overall, the proxy models can serve as low-cost surrogates for fault reproduction, targeted validation, and auxiliary diagnosis in RL post-training.

AI 总结：针对异构联邦系统的表示学习挑战，提出Sheaf-FRL框架，通过层束限制映射实现相邻潜在表示对齐，在协作分类任务中优于基线方法且鲁棒性更强。

链接：https://arxiv.org/abs/2608.10016

机构：Sapienza University of Rome（罗马第一大学）

作者：Gabriele D'Acunto, Enrico Grimaldi, Valeria Avino, Mario Edoardo Pandolfo, Leonardo Di Nino, Sergio Barbarossa, Paolo Di Lorenzo

英文摘要： Heterogeneous federated systems require agents to learn and exchange informative representations despite differences in data distributions, sensing modalities, model architectures, latent dimensionalities, and local learning objectives. To address this challenge, we propose Sheaf-based Federated Representation Learning (SFRL), a general framework that jointly optimizes local objectives with a manifold-constrained geometric alignment regularizer based on learnable sheaf restriction maps. Unlike most existing approaches, SFRL does not assume a shared global latent space. Instead, global consistency emerges from the alignment of neighboring latent representations through orthogonal transformations and isometric embeddings. This alignment is enforced by a quadratic gluing regularizer induced by the sheaf Laplacian, whose learnable restriction maps adapt the geometry to the observed data. The penalty is evaluated on a small set of shared pilot samples, ensuring scalability and communication efficiency. We develop a decentralized algorithm for solving SFRL, termed Sheaf-FRL, which alternates between gradient updates of the local models and closed-form Procrustes updates of the edge-wise restriction maps. We further establish convergence of Sheaf-FRL to first-order stationary points in both deterministic and stochastic settings. As an application, we consider a cooperative classification task in the context of semantic communication, under model and data heterogeneity. Our results show that Sheaf-FRL outperforms baseline approaches in terms of local and post-communication classification accuracy across different levels of local distribution shift and exhibits greater robustness to latent-space dimensionality compression.

AI 总结：Fisher8是一种输出层梯度修正方法，通过Fisher几何稳定神经异方差回归，无数据依赖超参数，在多维回归等任务中实现了更优的似然-误差权衡与校准不确定性估计。

链接：https://arxiv.org/abs/2608.10374

机构：University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

作者：Sumedh Vemuganti, Nickvash Kani

英文摘要：Training neural networks to jointly predict mean and uncertainty estimates from noisy observations can be unstable, prompting a series of independent stabilization efforts. We argue that these interventions highlight a common underlying issue where gradient steps are poorly aligned with the geometry of the loss landscape. To better align updates with local curvature, we derive Fisher8, an output-layer gradient correction that reorients and rescales updates using Fisher geometry rather than Euclidean geometry. Unlike past stabilizers, Fisher8 introduces no data-dependent hyperparameters beyond learning rate and admits an approximate KL trust radius between successive predictive distributions. We show that prior stabilizers converge on overlapping components of this geometric correction. Across multidimensional regression and representation-learning tasks, Fisher8 obtains superior likelihood--error tradeoffs, predicts calibrated uncertainty estimates, and learns rich uncertainty-aware feature spaces.

AI 总结：该研究提出一种无需条件分布的联合分布路径，以 HSIC 为实例实现公平表示学习，其收敛速度优于条件路径方法，对应算法 FRHSIC 能在保持公平性-准确性权衡的同时缩短训练时间。

链接：https://arxiv.org/abs/2608.10470

机构：Georgia Institute of Technology（佐治亚理工学院）

作者：Yijin Ni, Xiaoming Huo

英文摘要：Fair representation learning with a continuous sensitive attribute $S$ requires a representation $Z$ that is statistically independent of $S$. Existing criteria, including generalized demographic parity, the expectation of integral probability metrics (EIPM), and mutual information, enforce this independence by averaging a per-value discrepancy between the conditional law $P_{Z \mid S=s}$ and the marginal $P_Z$ over the law of $S$. This approach requires a nonparametric surrogate for the conditional law at each sensitive value. We propose evaluating independence through a single joint discrepancy $d\left(P_{Z, S}, P_Z \otimes P_S\right)$ between the joint law and the product of its marginals. We establish a disintegration identity; on decomposable witness classes it equals the conditional-integral functional that EIPM and generalized demographic parity instantiate. By reaching the same target without the conditional law, this discrepancy can be estimated directly from samples via a dependence statistic rather than conditional smoothing. We take the Hilbert-Schmidt independence criterion (HSIC) as an instance of the joint discrepancy $d$ to investigate the statistical efficiency of replacing the conditional formulation. The HSIC estimator is a closed-form $O\left(n^2\right)$ statistic that converges at the $O\left(n^{-1 / 2}\right)$ rate, in contrast to the nonparametric $O\left(n^{-2 / 5}\right)$ rate of the conditional-route estimators. We prove this instance is equivalent to the conditional maximum mean discrepancy (MMD) integral up to an explicit spectral tail. The corresponding algorithmic implementation, i.e., FRHSIC, attains fairness-accuracy tradeoffs comparable to conditional-route basel es while reducing per-epoch training time.

AI 总结：本研究提出FiGuRO框架，用于在模型容量与超参数约束下估计单/多模态数据的本征维度，可实现共享与私有信息解耦，性能优于现有技术且可应用于单模态预训练模型。

链接：https://arxiv.org/abs/2608.10857

作者：Viktoria Schuster, Sana Tonekaboni, Caroline Uhler

英文摘要： Determining the complexity, or Intrinsic Dimension (ID), of data is fundamental to efficient and interpretable representation learning. This is particularly challenging in multi-modal settings when trying to learn disentangled representations for shared and private information. Existing techniques leave a critical gap: they are often static, uni-modal, or in the case of contrastive methods, adapt only to the shared ID implicitly. We introduce Fidelity-Guided Rank Optimization (FiGuRO), a framework for approximating the ID of uni- and multi-modal data under constraints of model capacity and hyperparameters. FiGuRO learns the dimensions of low-rank projections using truncated singular value decomposition and an algorithm that determines when to reduce or increase dimension and in which latent space. Disentanglement of shared and private information arises as an emergent property of this optimization, eliminating the need for complex auxiliary loss functions. We demonstrate that FiGuRO outperforms existing ID estimation techniques and is more robust to hyperparameter changes. Across simulations and real-world data, FiGuRO captures distinct ID scales and varying subspace ratios, and decomposes shared and private information successfully. Furthermore, we show that FiGuRO can be applied to modern uni-modal pretrained models, enabling efficient, post-hoc disentanglement of multi-modal representations.

AI 总结：本研究构建三种互补差异度，分析32个大型语言模型的行为，发现模型家族形成聚类、跨家族距离随时间减小等规律，且该方法具有标签无关性与鲁棒性。

链接：https://arxiv.org/abs/2608.11027

作者：Dong Qiao, Chris Ding, Jicong Fan

英文摘要：Benchmark leaderboards summarize how well a language model performs, but not how its behavior relates to that of other models or changes across generations. We characterize the output behavior of 32 models from six families using their responses to a shared bank of 10{,}000 prompts. After embedding each response, we construct three complementary sentence-level dissimilarities: an aligned mean per-prompt distance, which is a pseudometric on observed model responses; a PCA-compressed summary of prompt-wise disagreement; and an alignment-free Gromov--Wasserstein discrepancy between models' internal response geometries. We use these constructions to study static organization and temporal change on a release-date axis through behavioral maps, family-wise drift, hierarchical clustering, cross-family convergence, and response-cloud dispersion. Across the three constructions, model families form coherent clusters, with \texttt{gpt-2} as a global outlier; cross-family distances decrease over time; and several recent reasoning-oriented models have comparatively compact response clouds. A token-level cross-check based on per-prompt Maximum Mean Discrepancy closely agrees with the sentence-level mean distance (Spearman $\rho=0.98$) and recovers the same qualitative findings. We organize these comparisons through a measure-theoretic lens making their alignment and invariance assumptions explicit. We also establish an architecture-agnostic sufficient condition linking behavioral similarity to inference-prompt coverage, small excess population log-loss, and similar effective target distributions---a possible training-side account rather than an empirical explanation of the observed trends. Our pipeline is label-free, and re-encoding every response with three further encoders---down to one $73\times$ smaller---preserves the rank geometry, the outliers, and the sign of the time trend.

AI 总结：该研究指出标准RLHF因偏好平均引发程序公平性失败，提出PA-RLHF分开优化不同偏好模式，提升了对齐准确率并缩小了群体公平差距，对大模型和智能体系统有重要意义。

链接：https://arxiv.org/abs/2608.10126

机构：Vishnu Institute of Technology（维什努理工学院）

作者：M P V S Gopinadh, Karthik Kamuju, Kummari Avinash, John Joshua, Srinivasa Raju Rudraraju

英文摘要：Reinforcement Learning from Human Feedback (RLHF) aggregates heterogeneous preferences into a single reward model, assuming preference homogeneity. When preferences are heterogeneous, this aggregation induces a procedural fairness failure where majority preference groups dominate reward learning while minority preferences are systematically under-represented. This work defines procedural fairness in alignment as preserving distinct preference signals during reward modeling and shows that standard RLHF violates this via preference averaging. Preference-Aware RLHF (PA-RLHF) is introduced, separating optimization across preference modes at the reward learning stage. In a controlled setting, PA-RLHF improves overall alignment accuracy from 46.9% to 67.9% and reduces the fairness gap between best and worst aligned groups from 15.9 to 9.6 percentage points. These results show that procedural fairness failures in alignment can arise from structural design choices in reward learning, even in controlled, noise-free settings, with direct implications for large language models and agentic systems, where biased reward models can compound inequities across sequential decisions.

AI 总结：本文提出BSPG算法，针对安全强化学习中标准梯度法易收敛到可行域内部的问题，结合切向与法向分量，在Safety-Gymnasium导航任务中实现更高奖励与更紧密的边界跟踪。

链接：https://arxiv.org/abs/2608.10204

机构：School of EECS, Washington State University（华盛顿州立大学电子工程与计算机科学学院）

作者：Chenhua Fan, Jiahui Zhu, Yuhang Zhang, Honghao Wei

英文摘要：Safe reinforcement learning maximizes reward subject to safety constraints. For Constrained Markov Decision Processes, the linear-programming view over occupancy measures implies that whenever the constraint is active at optimality, the optimal policy lies exactly on the constraint boundary, yet standard gradient-based methods do not exploit this structure and often settle in the feasible interior. We introduce Boundary-Seeking Policy Gradient (BSPG), a first-order method whose update combines a tangential component that improves reward while preserving cost to first order with a signed, residual-driven normal component that regulates the policy toward the active boundary from either side; the combined direction admits an algebraic Lagrangian form with an induced coefficient and no learned dual variable. Under exact gradients and stated regularity conditions, the constraint residual converges to zero from either side with a finite-horizon $O(1/\sqrt{T})$ bound, the tangential component is a reward-ascent direction on the boundary, and any convergent parameter sequence is stationary on the active constraint set, satisfying the KKT conditions when the limit is also a local maximizer over the feasible set. This complements existing analyses, which certify feasibility but do not characterize the constraint value at convergence. On a standard Safety-Gymnasium navigation task, BSPG attains higher reward while tracking the boundary more tightly than the compared baselines.

AI 总结：本文提出 SINKFLEX-RL 模块化训练系统，通过整合环境接口等技术，在 Tau2Bench 测试中提升验证奖励并降低注意力路径显存占用，实现长周期工具使用智能体的高效 RL 训练。

链接：https://arxiv.org/abs/2608.10357

机构：Capital One（第一资本金融公司）； AI Foundations（人工智能基础部门）

作者：Zelei Cheng, Amritansh Mishra, Sambit Sahu, William Campbell

英文摘要：Long-horizon tool-using agents must reason over user goals, domain policies, tool calls, simulator state, and delayed verifiable rewards. Reinforcement learning (RL) is a natural fit for this setting, but multi-turn on-policy rollouts create long contexts, while model-specific attention layers may require custom masks and learned sink normalization. We present SINKFLEX-RL, a modular training system for RL in dual-control tool-use environments. The system combines a Gymnasium-compatible environment wrapper, a VERL-style rollout dataflow, group-relative policy optimization without a separate value model, and a sink-aware FlexAttention path designed to preserve model-specific sink scaling under causal and sliding-window masks. In a preliminary Tau2Bench retail run, validation reward (mean@1) rises from 0.25 early in training to $0.44$ later in the observed training window, while training-score and trajectory-reward proxies also trend upward. In a fixed-configuration memory benchmark, the optimized attention path reduces peak VRAM from 28.06GB to 22.52GB at 4096 tokens, a $19.7\%$ reduction, and runs the measured 8192-token configuration using $25.53$~GB where the eager baseline runs out of memory. These results illustrate the value of integrating environment interfaces, RL dataflow, and attention-kernel design for memory-feasible long-horizon agent training.

AI 总结：本文提出Dreamer-SAC框架，结合循环状态空间世界模型与离线策略SAC算法，在自动驾驶场景中优于DreamerV3、SAC等基线，且所需真实环境交互更少。

链接：https://arxiv.org/abs/2608.10386

机构：Tongji University（同济大学）

作者：Jiazhuo Li, Linjiang Cao, Qi Liu, Xi Xiong

英文摘要：Sample-efficient reinforcement learning for autonomous driving is often limited by the trade-off between data efficiency and model bias. While world models reduce the reliance on costly environment interactions, policy optimization over learned dynamics remains sensitive to prediction errors. This paper proposes the Dreamer-SAC framework, which integrates a recurrent state-space world model with an off-policy soft actor-critic algorithm trained directly in latent space. The framework uses a combination of real interactions and short-horizon generated trajectories with n-step target estimation and multi-objective supervision. Evaluated in autonomous driving scenarios with objectives encompassing driving efficiency and safety, the proposed framework consistently outperforms representative reinforcement learning baselines, including DreamerV3, SAC, and PPO, while achieving improved performance with substantially fewer real environment interactions. Experiments reveal an inverted-U relationship between rollout horizon and policy performance, where short-horizon latent rollouts achieve the best trade-off between additional training signals and accumulated model bias. Furthermore, n-step target estimation demonstrates more effectiveness over one-step temporal-difference targets in exploiting predicted experience for value learning.

AI 总结：TideRL是一种就绪感知弹性RL系统，通过CTB、RA²P和ERS技术，在多轮智能体工作负载上大幅提升RL训练有效吞吐量，同时优化KV缓存命中率、训练时间和等待时间。

链接：https://arxiv.org/abs/2608.10402

机构：Tsinghua University（清华大学）； Zhongguancun Laboratory（中关村实验室）

作者：Yanyu Ren, Xizheng Wang, Xiao Liu, Bowen Lv, Hanchen Zhang, Shudan Zhang, Hanyu Lai, Shuai Wang, Li Chen, Dan Li, Jie Tang

英文摘要：Reinforcement learning (RL) for large language models is moving toward multi-turn agentic workloads, where rollout tasks repeatedly pause for external environments, resume with growing contexts, and finish at highly variable times. In this setting, RL training goodput, measured by training throughput, matters more than raw GPU occupancy: GPU waiting and repeated prefill recomputation are pure overhead. We present TideRL, a readiness-aware elastic RL system with Continuous Task Batching, Resource-Aware Ref-Actor Pipelining, and Elastic Resource Scaling. CTB preserves useful rollout state, $\textrm{RA}^2\textrm{P}$ selects between decoupled streaming and colocated aggregation from the ready backlog and arrival interval, and ERS moves ranks between rollout and training using the same readiness signals. Across text-only and multi-modal agentic workloads, TideRL improves RL training goodput by up to 5.6$\times$ over synchronous baselines and over 33% over asynchronous baselines, while reaching similar task performance. It also improves KV cache hit rate by 1.58$\times$, reduces per-step training time by up to 44.3%, and cuts total waiting time by up to 77.6%.

AI 总结：该研究针对离线转在线强化学习中复用离线评判者导致的适配问题，提出无评判者预训练范式，兼容主流算法且在多任务上表现更优。

链接：https://arxiv.org/abs/2608.10473

机构：Tsinghua University（清华大学）

作者：Daoyi Li, Yixian Zhang, Chao Yu, Wenbo Ding, Yu Wang

英文摘要：Offline-to-online (O2O) reinforcement learning aims to leverage policies pretrained on static datasets while improving them through online interaction. However, directly reusing an offline-trained critic can hinder online fine-tuning: as the policy and data distribution change rapidly, value estimates inherited from offline training may become misaligned with the online environment, leading to inaccurate policy improvement and inefficient exploration. To address this problem, we introduce \textbf{C}ritic-\textbf{F}ree \textbf{P}retraining: an efficient paradigm that completely abandons the approach of offline critic training, allowing a freshly initialized critic to adapt without inheriting biased estimates. CFP is compatible with various mainstream O2O algorithms and consistently matches or improves upon conventional O2O algorithms across a diverse set of tasks, with particularly pronounced gains on several challenging tasks.

AI 总结：本研究提出EDPFRL-IM框架，将内在动机探索与随机网络蒸馏引入个性化联邦强化学习，在保护客户端隐私的同时，提升了延迟和稀疏奖励场景下的策略个性化与样本效率。

链接：https://arxiv.org/abs/2608.10499

作者：Md Rafid Islam, Rafsan Jany, Zahid Hasan, Ratun Rahman

英文摘要：Personalized Federated Reinforcement Learning (PFRL) takes a decentralized approach to storing and accessing information based on past experiences while keeping each client's data private during the learning of each client's policy. Many current methods for PFRL rely heavily on exploiting existing reinforcement learning reward signals to derive an optimal policy for each client, thereby neglecting exploration in non-stationary or sparse-reward environments. In this work, we introduce a new exploration-driven framework, Exploration-Driven Personalized Federated Reinforcement Learning via Intrinsic Motivation (EDPFRL-IM), that leverages an inherent curiosity-driven exploration at each client to promote local exploration and protect client privacy. Furthermore, to facilitate policy discovery via exploration in previously unexplored state spaces, clients add an intrinsic random network distillation (RND) signal to their extrinsic reward. Additionally, the server does not have access to clients' raw experiences or local gradient estimates; instead, the server sends global exploration priors and collects minimal novelty summaries from each client to enable both diverse and coordinated exploration among clients. Experiments in benchmark environments show that our framework outperforms average PFRL benchmarks in policy personalization and sample efficiency, primarily in delayed and sparse reward systems. Overall, EDPFRL-IM enables the integration of a flexible exploratory learning structure into federated reinforcement learning systems while preserving client privacy.

AI 总结：针对连续动作空间中利普希茨常数未知的协作多智能体老虎机问题，设计适配三种信息结构的算法，证明共享奖励或可观测动作可免费达成离散化一致性，否则通过抖动量化估计值达成且不增加悔的主阶成本。

链接：https://arxiv.org/abs/2608.10526

作者：Ricardo Parada, Chenzhang Zhao, William Chang

英文摘要：Motivated by decentralized applications, we study cooperative multi-agent bandits in continuous (Lipschitz) action spaces when the Lipschitz constant is unknown. We consider three information structures: (A)~unobserved actions with common rewards, (B)~observed actions with independent rewards, and (C)~unobserved actions with independent rewards. In each case we design and analyze an algorithm that estimates the Lipschitz constant, chooses a discretization of the joint action space, and applies a cooperative bandit method to the induced discrete problem. Players never communicate once learning starts, so the central difficulty is that they must reach the \emph{same} discretization from their own data. We prove regret guarantees showing that common rewards and observable actions each supply this agreement for free, and that in their absence agreement can still be bought, through a dithered quantization of the estimate, at no cost in the leading order of the regret.

AI 总结：该研究针对重尾奖励和信息不对称的多智能体多臂老虎机问题，为三种信息不对称场景开发鲁棒分散式算法，通过实验验证了理论结果并阐明相关权衡。

链接：https://arxiv.org/abs/2608.10529

作者：Daphne Feng, Ricardo Parada, Lily Jiang, Sophia Yi, William Chang

英文摘要：The multi-armed bandit problem is a central framework in sequential decision-making, extensively studied under sub-Gaussian reward assumptions. However, real-world applications often involve heavy-tailed reward distributions and decentralized, information-asymmetric interactions. We study multi-agent multi-armed bandits with heavy-tailed rewards under three information-asymmetry regimes: unobserved actions with common rewards, observed actions with independent rewards, and unobserved actions with independent rewards. We develop robust decentralized algorithms for each setting and derive regret guarantees that nearly match centralized heavy-tailed rates. Experiments on a Pareto-distributed reward environment validate our theoretical findings and illustrate the trade-offs between synchronization, coordination, and exploration across the three regimes.

AI 总结：MARCO框架通过按意图分解点击解决广告转化预测的校准偏差，经离线在线验证，部署后各意图校准近100%，每点击转化率提升2.80%，核心指标累计提升0.98%。

链接：https://arxiv.org/abs/2608.10562

机构：Meta AI

作者：Shiwen Shen, Xiru Huang, Liang Luo, Jianbo Sun, He Lyu, Zihang Fu, Ivonne Xu, Zhizhuo Li, Zhengyu Zhang, Pei-Ju Sung, Yunmiao Wang, Zixuan Wang, Zhengli Zhao, Qiang Jin, Mike Jermann, Mingda Li, Yang Xiao, Bhavana Challa, Brooke Bian, Yang Li, Ashish Chamoli, Bibek Bhusal, Danning Di, Yuan Jin, Meet Raval, Zhiwen Chen, Boyao Sun, Shuguang Wang, Yunlong He, Yantao Yao, Sagar Chordia, Wenlin Chen, Santanu Kolay, Qin Huang, Ellie Wen

英文摘要：Not all clicks are equal. Industrial ads ranking decouples conversion probability into click-through rate (CTR) and post-click conversion rate (CVR), yet treats every click as the same event. In reality, users provide a free, self-generated signal of intent through their physical UI interactions. Different click types on the same ad exhibit a 4-fold difference in actual conversion rates. By conflating these signals, the standard CVR model under-predicts high-intent clicks and over-predicts low-intent ones, which is a bias masked by near-perfect aggregate calibration. We propose MARCO (Multi-intent Ads Ranking Composition Optimization), a framework that resolves this bias by decomposing each click by intent. Using the logged click type as a free behavioral label, MARCO trains per-intent CVR heads on homogeneous populations, and at serving time composes their per-intent CVR estimates under a predicted distribution over intents. Theoretically, we prove that decomposition never raises population risk, give the exact headroom under squared loss and non-negativity under the deployed loss, and show through a routing-efficiency dial how much of it reaches serving. Because the population-optimal score is unchanged, any gain is a finite-capacity estimation and calibration effect that we validated both offline and online. For deployment at scale, we further cast multi-impression, multi-click attribution as credit assignment with a bias-variance tradeoff analogous to RL return estimation, showing last-impression, first-click attribution is the low-bias, low-variance, deterministic choice under production constraints, and derive three consistency conditions enforced end-to-end at scale. Deployed at binary intent granularity, MARCO corrects per-intent calibration to approximately 100%, lifts conversions per click by +2.80%, and drives +0.98% cumulative improvement in topline metrics.

AI 总结：本文提出IADD-TR框架，通过干预感知动力学解耦与定向正则化解决MBRL中策略诱导的数据偏差问题，经MuJoCo任务实验验证可提升样本效率并取得有竞争力回报。

链接：https://arxiv.org/abs/2608.10634

机构：School of Computer Science, Guangdong University of Technology（广东工业大学计算机学院）； College of Science, Shantou University（汕头大学理学院）

作者：Zefeng Liang, Jie Qiao, Ruichu Cai, Weilin Chen, Zhifeng Hao

英文摘要：Model-based reinforcement learning (MBRL), which learns environment dynamics to generate synthetic experience, is a promising approach to sample-efficient decision making. Numerous methods have been developed to improve dynamics prediction and policy optimization for MBRL through uncertainty estimation, model regularization, and conservative value learning. However, these methods typically treat the transition model and critic as monolithic predictors, overlooking the policy-induced data bias. Consequently, action can become entangled with environmental evolution, while uneven action coverage may distort the counterfactual value estimates used for policy improvement. To address this, we propose IADD-TR, a unified framework combining Intervention-Aware Dynamics Decoupling (IADD) and Targeted Regularization (TR). IADD factorizes transitions into an action-intervention stage and an action-free natural evolution stage, using a zero-action anchor to resolve the non-uniqueness of this two-stage factorization for robust generalization. Its latent and state-aligned components are identifiable up to an invertible within-block transformation and pointwise, respectively. For policy learning, we derive TR from the efficient influence function of a replay-state policy-gradient functional. TR augments the critic with an action-density-scaled residual correction and optimizes a targeted loss, yielding doubly robust policy-gradient estimation when either the critic or the replay action density is consistently specified. Extensive experiments on five MuJoCo tasks show that IADD-TR achieves competitive returns with improved sample efficiency.

AI 总结：本文针对多平台即时配送调度的部分可观测问题，提出POLO框架，通过建模平台-网格智能体、注意力策略表示与反事实奖励塑形，在多场景下实现优于基线的调度性能

链接：https://arxiv.org/abs/2608.10897

机构：University of Exeter（埃克塞特大学）

作者：Fengming Yao, Man Luo

英文摘要：Instant delivery platforms have become a critical component of urban logistics, increasingly relying on crowdsourced couriers to fulfill highly dynamic orders. In real-world systems, couriers are not exclusive to a single platform and may concurrently serve multiple platforms, while each platform can only observe its own orders and couriers' interactions due to privacy and operational constraints. This results in a multi-platform dispatch environment with inherent partial observability. However, most existing works on dispatch optimization assume full courier observability and mandatory assignment acceptance, causing substantial performance degradation when deployed in realistic multi-platform settings. In this paper, we propose POLO, a partially observable multi-agent reinforcement learning framework for dispatching optimization in multi-platform instant delivery systems. POLO firstly models each platform-grid pair as an independent agent that learns dispatch policies solely from platform-local observations, aligning the learning process with real-world privacy and operational constraints. To support effective decision-making under incomplete and heterogeneous courier information, POLO introduces a novel attention-based policy representation that selectively aggregates inter-courier information. Moreover, we design a counterfactual reward shaping mechanism to mitigate the non-stationarity induced by joint actions across grids, leading to more stable and scalable learning. We develop a high-fidelity simulator to evaluate dispatch performance under varying numbers of platforms and system scales. Extensive experiments demonstrate that POLO consistently outperforms strong baselines in terms of platform revenue and courier travel efficiency, highlighting its robustness and effectiveness in realistic multi-platform settings.

AI 总结：该研究针对逆强化学习双层优化的计算挑战，利用策略费舍尔信息矩阵的特性设计结构化超梯度，通过流式频谱草图近似逆费舍尔向量乘积，在控制环境中实现了高效且性能良好的IRL方法。

链接：https://arxiv.org/abs/2608.11052

机构：HSE University（高等经济大学）

作者：Nikita Sevriukov, Anna Barabanova, Uliana Gagarina, Karina Ivanova, Sofiia Kasaeva, Ilya Levin, Marina Sheshukova

英文摘要：Inverse reinforcement learning (IRL) aims to recover a reward function under which the resulting policy reproduces the behavior observed in expert demonstrations. A natural approach is to formulate IRL as a bilevel optimization problem, in which the inner level corresponds to policy optimization under the learned reward and the outer level measures the discrepancy between the induced policy and expert data. However, this formulation is computationally challenging in practice because the outer update requires a hypergradient involving an inverse-Hessian-vector product for the inner objective. We address this challenge by showing that, at the inner optimum, the Hessian of the inner objective is proportional to the Fisher information matrix of the policy, yielding a structured Fisher-based hypergradient closely related to Natural Hypergradient Descent. To address the resulting scalability bottleneck associated with large Fisher matrices, we approximate the required inverse-Fisher-vector product using a streaming spectral sketch, avoiding explicit construction of the Fisher matrix. We evaluate our approach against a first-order stochastic bilevel baseline across discrete- and continuous-control environments. The results demonstrate competitive policy performance and strong reward-ranking quality, while Fisher sketching reduces curvature-storage complexity and can improve computational efficiency relative to an explicit Fisher solver.

AI 总结：本文针对Lévy驱动生成模型的非局域反向过程挑战，提出生成器引导的结构化逆采样器，将动力学分解为三类分量，结合神经网络与解析分布实现高效采样，在OFDM-SISO信道估计中表现出稳健性能与良好权衡。

链接：https://arxiv.org/abs/2608.10384

机构：University of Electronic Science and Technology of China（电子科技大学）； Hong Kong University of Science and Technology（香港科技大学）

作者：Tianfu Qi, Jun Wang, Jun Zhang

英文摘要：This paper studies inverse sampling for Lévy-driven generative models from the perspective of Markov generators. Unlike conventional diffusion models, Lévy-driven dynamics involve infinite jump activities, which makes their reverse process nonlocal and difficult to characterize using score information alone. We address this challenge by analyzing the forward and reversed generators. It is derived that the reversed jump component generally becomes a state-dependent Markov jump process governed by a nonlocal density ratio. This observation motivates a structured reverse sampler that decomposes the dynamics into diffusion, small jump, and large jump components. Based on this characterization, we develop a computationally tractable sampler for a class of isotropic linear Lévy SDEs with symmetric $\alpha$-stable jump components. For the jump component, the neural network is used only to amortize the rate of large jump activities, while jump amplitudes are generated from analytically derived conditional distributions, which improves interpretability and controllability. Efficient implementation techniques are further introduced under this setting to avoid expensive high-dimensional integration and sampling. The sampler is further adapted to approximate observation-guided sampling and applied to OFDM-SISO channel estimation under mixed Gaussian and impulsive noise. Simulations show robust estimation performance with a favorable tradeoff between complexity and performance.

AI 总结：该研究提出基于证据学习的变分自编码器ELVAE，通过显式建模潜在位置不确定性，在MNIST生成实验中验证其可分层生成样本的语义可靠性，为不确定性感知生成提供实用控制变量。

链接：https://arxiv.org/abs/2608.10398

机构：Rensselaer Polytechnic Institute（伦斯勒理工学院）

作者：Ge Wang

英文摘要：Variational autoencoders generate samples from probabilistic latent representations but do not distinguish uncertainty about the latent location from variability around it. We formulate ELVAE, an evidential learning-based VAE in which each latent coordinate is governed by an input-dependent normal-inverse-gamma posterior. This hierarchy yields an explicit latent-location uncertainty that can be used during generation, not merely reported after inference: low-uncertainty anchors support more reliable synthetic samples, while high-uncertainty anchors can be deliberately exploited for stress testing. The objective is an exact evidence lower bound, and we show that direct regularization of the full hierarchy is required, since the marginalized latent law alone cannot identify the uncertainty decomposition. In an MNIST generation pilot with a frozen external classifier, this uncertainty clearly stratified the semantic reliability of generated digits. A zero-displacement control revealed that most of the effect reflects how reliably an anchor can be re-generated, while a smaller but distinct component is attributable to uncertainty-scaled perturbation itself. The effect holds only under within-class uncertainty ranking, and its magnitude varies across seeds. These findings support the learned latent-location uncertainty as a practical control variable for uncertainty-aware generation, separating anchor reliability from perturbation-induced failure.

AI 总结：该研究针对WorldClim上训练的全连接非线性VAEs，探究β-VAE的频谱截断特性，发现非线性相互作用会改变折叠起始点但保留效用排序，且深度存在头尾权衡。

链接：https://arxiv.org/abs/2608.10599

机构：Universitat de València（瓦伦西亚大学）

作者：Johannes Hirn

英文摘要：In a $\beta$-VAE, increasing the regularization strength acts as a spectral cutoff by collapsing low-utility latent coordinates. In the linear Gaussian VAE, the collapse order matches the ranking of reconstruction utilities exactly, because both are set by the PCA spectrum. We ask which parts of this picture survive in fully connected nonlinear VAEs trained on WorldClim. We find that nonlinear interactions shift and broaden collapse onsets, so thresholds no longer coincide exactly with utilities. However, the common ordering is preserved over the resolved ranks, so the spectral cutoff still acts as a utility cutoff and the effective-description logic carries through. The resulting effective-dimension curves reveal a head--tail tradeoff: increasing depth concentrates utility into the first few coordinates but worsens tail fidelity.

AI 总结：本研究提出一种引入上下文特征的DNN优化方法，结合随机张量分解策略降低存储成本，实现5至40维高维函数的高效学习。

链接：https://arxiv.org/abs/2608.10351

机构：The University of Maryland（马里兰大学）； The University of Chicago（芝加哥大学）

作者：Karl Pierce, Yuehaw Khoo, Haizhao Yang

英文摘要：In this work we present a method to accelerate the optimization of learning high dimensional functions using deep neural network (DNN). This optimization procedure introduces contextual features into the first layer of a DNN. The parameters of DNN are optimized via standard gradient descent while keeping the input-feature basis fixed. After optimization of the DNN parameters, the feature layer is provided a chance to update and change before DNN optimization resumes. The feature layer has two types of functions: those that can be evaluated quickly in a matrix-free way on the domain (i.e. rank-1 features) and more complex features that must first be decomposed using tensor network (TN) decomposition strategies (tensor features). In particular, we study the effect of adding features which distill pretrained DNN into TNs using a discretize and decompose strategy. To efficiently decompose high-dimensional functions constructed from discretized DNN, we leverage a randomized tensor decomposition strategy. Using randomization, we are able to reduce the storage cost of decomposing high dimensional functions by at least 8 orders of magnitude. Using this approach, we are able to efficiently train models between 5 and 40 dimensions.

AI 总结：本文提出以对为中心的图重连框架PairAlign，结合结构需求与传播支持，引入最优传输引导的重连机制，在图基准实验中提升了消息传递骨干网络缓解过压缩的性能。

链接：https://arxiv.org/abs/2608.10619

机构：School of Mathematics, Sun Yat-sen University（中山大学数学学院）

作者：Yan Wang, Chuan-Xian Ren

英文摘要：Message-passing neural networks (MPNNs) often struggle when task-relevant information is distributed across distant regions of a graph, since local propagation must compress remote signals through limited structural interfaces. Graph rewiring provides a structural response to over-squashing. Most existing methods rely on edge-level bottleneck scores or graph-level connectivity surrogates. With a limited rewiring budget, the key question is which pairwise communications most need structural support. This paper proposes PairAlign, a pair-centric graph rewiring framework that makes this question explicit through demand-support shortage. Specifically, PairAlign combines original-graph structural demand with current-graph finite-hop propagation support; their ratio highlights interactions whose communication demand is poorly supported by topology, and our theory shows that this score provides a computable proxy for the corresponding Jacobian-based shortage with a pair-level interpretation of over-squashing. Our theory reveals a two-sided effect of edge insertion: a new edge can create useful walks and simultaneously dilute existing normalized transition mass. Guided by this observation, PairAlign optimizes shortage to favor edge additions that alleviate over-squashing. Beyond selecting useful additions, PairAlign further introduces an Optimal Transport-guided rewiring mechanism to coordinate the finite edge budget for pair-level structural compatibility and shortage-target coverage. It formulates communication alignment between the candidate edge budget and the shortage targets, and the theory shows that this allocation covers shortage targets more broadly and effectively than a greedy-local assignment. Experiments on standard graph benchmarks show PairAlign's improvement across message-passing backbones, validating pair-level repair as an effective route for alleviating over-squashing.

AI 总结：本文探究在适度评估预算下，贝叶斯优化能否在神经丛中高效找到强单专家，提出在权重空间随机线性嵌入中应用贝叶斯优化的无梯度方法，在Qwen2.5-Instruct模型基准测试中，该方法评估成本更低且性能优于随机优化。

链接：https://arxiv.org/abs/2608.10867

机构：University College London（伦敦大学学院）； Institut Polytechnique de Paris（巴黎理工学院）； University of Oxford（牛津大学）

作者：Nigel Bastian Cendra, Abdelhamid Ezzerg, Fernando Julio Cendra, Jeremias Knoblauch, Jakob Zeitler

英文摘要： Gradient-free post-training has emerged as a compelling alternative to gradient-based optimization for large language models (LLMs), but existing approaches remain costly. We ask whether structured search can identify a strong single expert under a modest evaluation budget. Motivated by evidence that useful weight updates lie in low-dimensional subspaces, we apply Bayesian optimization within a random linear embedding of weight space. Our method requires no backpropagation and uses a Gaussian process surrogate to guide candidate evaluations efficiently. Across several reasoning benchmarks with Qwen2.5-Instruct models from 0.5B to 3B parameters, Bayesian optimization using five times less candidate evaluations matches or exceeds RandOpt. These results show that surrogate-guided search can substantially reduce the evaluation cost of gradient-free post-training while producing stronger deployable single experts.

AI 总结：

链接：https://arxiv.org/abs/2608.10869

机构：University of New South Wales（新南威尔士大学）； University of Sydney（悉尼大学）

作者：Xiaoyu Li, Andi Han, Jiaojiao Jiang, Junbin Gao

英文摘要：Worst-case multiclass bounds do not become smaller when the best classifier is already nearly correct: what is missing is an optimistic rate, a guarantee whose fluctuation scales with the oracle risk itself. For a class of Natarajan dimension $d_N$ and Daniely-Shalev-Shwartz dimension $d_{DS}$, the optimal excess risk is known at the two endpoints ($d_{DS}/n$ realizable, $\sqrt{d_N/n}+d_{DS}/n$ agnostic [HMZ24, CEH+26, Pab26]) and open in between. We close the gap: at every fixed oracle risk $L^\star$, the optimal excess risk is $\widetilde{\Theta}(\sqrt{L^\star d_N/n}+d_{DS}/n)$, uniformly in the alphabet size, attained by a learner that knows neither $L^\star$ nor the confidence level. The upper bound composes the cover-menu-compression architecture of [CEH+26], at the realizable rate of [Pab26], with a new comparator-facing relative compression theorem: a size-$k$ compression rule that empirically dominates a comparator $h$ has population risk at most $L(h)+O(\sqrt{L(h)\Gamma}+\Gamma)$ with $\Gamma=(k\log n+\log(1/\delta))/n$, without stability; this transfers the comparison principle of the sharp binary theory [MQZ26] while discarding its Boolean-cube geometry, which does not lift to multiclass labels. The lower bound forces both terms using one class and one distribution at every fixed $L^\star$, by a pair-Assouad scheme calibrated to $L^\star$ and a fiber argument on the pseudo-cubes underlying the Natarajan-versus-DS separation of [BCD+22]. Both theorems extend to list learning: against the best $r$-tuple of hypotheses, the same architecture and the same two engines yield an optimistic rate and a lower bound of the same shape, forcing the fluctuation term that [Pab26] expected to be necessary against list comparators, and removing the factor $r$ from the known realizable list lower bound.

AI 总结：DEFT是一种频域数据采样方法，通过逆离散傅里叶变换生成物理一致的训练数据，可减少数据需求且提升泛化能力，在多个PDE及电池退化系统建模任务中表现优异。

链接：https://arxiv.org/abs/2608.11019

机构：Peking University（北京大学）

作者：Hengbo Xiao, Jiale Liu, Jiahao Song, Guannan He

英文摘要：Modeling spatiotemporal dynamical systems governed by partial differential equations (PDEs) poses two major challenges: it either requires expensive physics-based simulators that entail iterative numerical solving at high computational cost, or it depends on abundant training data, yet purely data-driven models often generalize poorly to downstream dynamic operating conditions. We propose DEFT, a frequency-domain data sampling method that identifies the dominant Fourier modes of a physical system and systematically varies the corresponding amplitudes and phases to generate physically consistent training data via the inverse discrete Fourier transform. In addition, we derive a generalization bound of this method. We note that it also provides a theoretically principled criterion for selecting $K$. We evaluate the proposed method through three sets of experiments, each targeting a distinct aspect of its utility. First, we validate the framework on canonical PDEs solving demonstrating that it outperforms traditional methods when the system is dominated by a few prominent frequency components. Second, we employ DEFT as a data-value filter on the diffusion--sorption and Burgers equations of PDEBench, showing that it reduces data requirements by $40\%$ while sacrificing less than $2\%$ in predictive accuracy. Third, to evaluate DEFT for more challenging and practically relevant problems, we validate it in the battery degradation PDE system, achieving consistently high predictive accuracy across various test datasets with $R^2$ values exceeding $0.99$. Moreover, the learned frequency-domain features transfer to other battery chemistries with only $20\%$ of the fine-tuning data. These results demonstrate that DEFT is an effective data-sampling method for efficient operator learning.

AI 总结：该研究针对量化感知训练结合知识蒸馏的损失下界问题，提出SQuaT框架，通过学生量化参数量化教师特征消除下界，在低比特设置下性能优于基线，适用多种架构。

链接：https://arxiv.org/abs/2608.10709

机构：Kookmin University（国民大学）

作者：HyeonJun Lee, Hyeonsik Jo, Jinwoo Chung, Jangho Kim

英文摘要： Quantization-Aware Training (QAT) enables the deployment of quantized models with minimal accuracy degradation. However, in practical scenarios, training labels are often unavailable due to privacy, copyright, or cost constraints. Knowledge Distillation (KD) is a common approach to address this challenge, but we observe that prior work combining QAT with KD suffers from a fundamental limitation: during distillation, the range mismatch between the teacher and the quantized student model induces an unattainable residual, resulting in an irreducible lower bound on the distillation loss. Motivated by this observation, we propose SQuaT (Student-Aware Quantized Teacher Features), a label-free QAT framework with KD that theoretically eliminates this lower bound by applying the student's quantization parameters to quantize the teacher's features during distillation. Through comprehensive experiments across diverse settings, we demonstrate that SQuaT consistently outperforms strong baselines, with particularly pronounced gains in extreme low-bit (e.g., 1- and 2-bit) settings. Furthermore, extensive evaluations across various model design choices show that our approach does not rely on specific architectural assumptions, making it broadly applicable across diverse architectures and quantization settings. The source code is available at this https URL.

AI 总结：ReRound是一种后训练量化方法，通过条件扩散模型解决无校准LLM量化的中点歧义，在小型LLM的3、4比特量化上优于标准RTN，性能接近依赖校准方法且无额外推理开销。

链接：https://arxiv.org/abs/2608.11045

作者：He-Yen Hsieh, H. T. Kung

英文摘要：ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inherent in standard round-to-nearest (RTN) schemes when quantizing weights near the centers of quantization intervals. Starting from a pretrained LLM, ReRound trains a conditional diffusion model to produce continuous reconstructions of low-bit weights for the LLM. These reconstructed weights act as a guidance signal to disambiguate the rounding direction of weights located close to interval midpoints. To integrate this reconstruction-guided rounding with conventional RTN, ReRound introduces a tolerance metric measuring how far the quantized weight (not the final quantized integer) is away from the midpoint: quantized weights within a tolerance region around midpoints are quantized using diffusion-based reconstructions, whereas weights closer to quantization boundaries are quantized with RTN. By sweeping the tolerance parameter, ReRound generates multiple candidate quantized integer weight matrices and selects the de-quantized weight matrix candidate whose leading singular values most closely match those of the original full-precision weights. This selected candidate determines the tolerance parameter ReRound uses. ReRound is particularly effective for smaller LLMs. Across a range of such models, it consistently outperforms standard RTN for 3-bit and 4-bit weight quantization. ReRound achieves superior accuracy compared to an extensive set of calibration-free methods, remains competitive with calibration-dependent approaches, and operates entirely offline, introducing no additional overhead during low-bit inference. The ReRound strategy represents a new approach for low-bit quantization. The method applies to AI models beyond LLMs. This paper focuses on its applications to small LLMs.

AI 总结：研究针对现有LLM安全防护的确定性范式局限，提出概率架构无关防护框架ProbGuard，利用早期输出分布信号校准安全风险，实现提前终止不安全输出，在9种组合设置及6种越狱攻击中均表现优异。

链接：https://arxiv.org/abs/2608.10621

作者：Xinzhe Huang, Biwu Yao, Kedong Xiu, Mengnan Zhao, Di Wang, Puning Zhao, Tianhang Zheng

英文摘要：Recent research on Large Language Model (LLM) safety has widely adopted guardrails to identify unsafe LLM outputs. Existing guardrails typically formulate safety assessment as a deterministic classification task, mapping a discrete token sequence to a discrete safety label. However, this paradigm has two limitations: First, safety assessment is inherently an uncertain problem, particularly during the early generation state. Second, relying solely on discrete token sequences discards the rich probabilistic information embedded in the LLM output distribution. To address these limitations, we propose the first completely probabilistic architecture-agnostic guardrail \textsc{ProbGuard} to leverage the LLM early output distributional signals for estimating and calibrating the safety probability, thereby enabling early stopping of unsafe ongoing outputs. Specifically, given an LLM's generated prefix distribution, we formulate the safety risk as the unsafe probability of its continued generation dynamics and estimate this risk by Monte-Carlo sampling. Through post-training on the distributional signals and calibrated safety risk, \textsc{ProbGuard} achieves the best calibration performance across all nine model--dataset combination settings, reducing the average Brier score and ECE by 79.6\% and 71.9\%, respectively, over the best baseline. \textsc{ProbGuard} further limits the attack success rate to at most 1\% across six representative jailbreak attacks after observing the LLM early output distributions from only the first ten decoding steps.

AI 总结：本研究通过对比三种不确定性量化方法，分析其在基因组学两类应用中的表现，明确了贝叶斯神经网络的优势，为基因组学UQ方法的应用提供了指南。

链接：https://arxiv.org/abs/2608.11054

机构：The Berlin Institute for Medical Systems Biology（柏林医学系统生物学研究所）； Max Delbrück Center for Molecular Medicine（马克斯·德尔布吕克分子医学中心）； Technical University of Berlin（柏林工业大学）； Humboldt University of Berlin（柏林洪堡大学）

作者：Sepideh Saran, Mahsa Ghanbari, Uwe Ohler

英文摘要： Deep learning models have emerged as the standard computational tool for a wide range of applications in genomics. Yet, uncertainty quantification (UQ) -- and more specifically, the reliability of different uncertainty estimates in this domain -- has received little systematic attention. This work presents an empirical analysis of UQ in deep learning models, focusing on genomics applications. In a series of experiments, we contrast Deep Ensembles, Bayesian Neural Networks, and Monte Carlo-dropout methods. We assess their ability to quantify uncertainty in different scenarios, accounting for common dataset characteristics in two genomic application areas and modalities: sequence-to-activity models, and single-cell expression analysis. Our systematic comparison framework provides guidelines for the applicability and reliability of UQ methods in genomics, highlighting their strengths and limitations in different scenarios. We show that Bayesian Neural Networks are better at capturing uncertainty caused by strong class imbalance and out-of-distribution data in genomics, despite their computational disadvantages. Moreover, we show how uncertainty scores can be used to select high-quality predictions in protein-RNA interactions.

AI 总结：该研究提出CriticalSCM-Bench v1基准，对比LambdaMART与恒定缓冲策略等，明确自适应干预排名在关键供应链场景的适用范围及模型复杂度的价值边界。

链接：https://arxiv.org/abs/2608.11154

机构：Independent Researcher（独立研究者）

作者：Shiqi Huang, Jiani He, Dingyan Shang, Yihua Xu, Jize Li, Yan Lyu, Lashimi Muraleedharan Nair

英文摘要：Detecting or attributing a supply-chain disruption is not the same as selecting the intervention that maximizes recoverable net value. We present CriticalSCM-Bench v1, a controlled synthetic benchmark with causal ground truth, paired factual/counterfactual rollouts, and an explicit net-value objective. Relative to a full-information train-selected static benchmark, LambdaMART improves median normalized net value by 5.7--16.2\%, with paired statistical support on the semiconductor and critical-material archetypes but not on digital infrastructure. On digital infrastructure, a domain-informed constant-buffer policy remains stronger, showing that greater model complexity is not uniformly justified. Across partial and delayed settings, LambdaMART retains 33--75\% of full-clamp value. Stress tests further show that intervention fidelity, timing, cost, and held-out disruptions can alter policy ordering. Critical materials show the weakest out-of-distribution retention. Separately, a guarded explanation study over 540 generations preserves every fixed intervention decision after deterministic validation and template fallback, although exact wording remains unstable. Within this controlled setting, the results identify regimes in which adaptive ranking adds value and those in which simpler structural policies remain preferable.

AI 总结：该研究提出HEB-NB及HEB-AODE，解决NB固定平滑强度致高基数表格数据偏差问题，经31个基准测试，其在概率指标、对数损失及ECE上均有显著改进。

链接：https://arxiv.org/abs/2608.11162

机构：Van Lang University（范朗大学）； Ho Chi Minh City University of Transport（胡志明市交通大学）

作者：Nguyen Thai Anh, Truong Viet Vu, Tran Thien Thanh, Vo Nguyen Quoc Bao, Ngo Hoang Tu

英文摘要：The Naive Bayes (NB) classifier remains a standard choice for categorical data, yet its widely used smoothing rules, such as Laplace, Lidstone, Krichevsky-Trofimov, and the $m$-estimate, all prescribe a fixed smoothing strength that ignores feature cardinality, sample size, and class imbalance, inducing a non-vanishing bias on modern high-cardinality tabular data. We propose hierarchical empirical-Bayes Naive Bayes (HEB-NB), in which each class-feature conditional probability is smoothed by a Dirichlet prior whose concentration is learned data-adaptively via Type-II maximum likelihood, enabling principled information sharing across classes while retaining closed-form inference. We further introduce HEB average one-dependence estimators (HEB-AODE), showing that the adaptive smoothing transfers cleanly to structural relaxations of NB. Theoretically, we establish a non-asymptotic $\ell_1$ error bound for HEB-NB matching the empirical-distribution minimax rate plus a vanishing data-adaptive bias, together with a matching Laplace-tight lower bound that yields a finite-sample, risk-level strict separation from Laplace. We further derive a plug-in excess Bayes-risk bound via total-variation tensorization and a population top-1 expected calibration error (ECE) corollary. Empirically, across 31 UCI and OpenML benchmarks, HEB-NB attains the best average Friedman rank on probabilistic metrics, with up to 22.1% log-loss reductions on high-cardinality datasets and consistent improvements of HEB-AODE over vanilla AODE. Combining HEB-NB with mutual-information weighting reduces top-1 ECE by 41%-70%, demonstrating substantial gains in probabilistic accuracy and calibration.

AI 总结：本文提出GARLIC模型，通过可学习指数衰减编码器等模块处理ICU多变量时间序列，在三个ICU基准数据集上实现结局预测最优，兼具可解释性与泛化性。

链接：https://arxiv.org/abs/2608.10969

机构：University of Zürich（苏黎世大学）； ETH Zürich（苏黎世联邦理工学院）； SPF； SCAI Lab（SCAI实验室）； D-HEST

作者：Ruirui Wang, Yanke Li, Manuel Günther, Diego Paez-Granados

英文摘要： Healthcare data, such as Intensive Care Unit (ICU) records, comprise heterogeneous multivariate time series sampled at irregular intervals with pervasive missingness. However, clinical applications demand predictive models that are both accurate and interpretable. We present our Graph Attention-based Relational Learning for Intensive Care (GARLIC) model, a novel neural network architecture that imputes missing data through a learnable exponential-decay encoder, captures inter-sensor dependencies via time-lagged summary graphs, and fuses global patterns with cross-dimensional sequential attention. All attention weights and graph edges are learned end-to-end to serve as built-in observation-, signal-, and edge-level explanations. To reconcile auxiliary reconstruction and primary classification objectives, we developed an alternating decoupled optimization scheme that stabilizes training. On three ICU benchmarks (PhysioNet 2012 & 2019, MIMIC-III), GARLIC sets the new state of the art in outcome prediction, significantly improving AUROC and AUPRC over best-performing baselines at comparable computational cost. Ablation studies confirm the contribution of each module, and feature-removal trials validate the fidelity of importance attribution through a monotonic performance drop (full > top 50% > random 50% > bottom 50%). Real-time case studies demonstrate actionable risk warnings with transparent explanations, marking a significant advance toward accurate, explainable deep learning for irregularly sampled ICU time series data. Moreover, we demonstrated \proposed{}'s superiority in data imputation and classification on various time-series datasets beyond the ICU domain, showing its generalizability and applicability to broader tasks.

AI 总结：针对联邦LoRA中客户端秩异构导致的双线性不匹配问题，提出SeFoRA算法，引入SeFoRA-Ho秩齐次版本，理论保证收敛速率，在GLUE数据集上验证其性能优于现有最优方法。

链接：https://arxiv.org/abs/2608.10144

机构：Technical University of Munich（慕尼黑工业大学）； Technische Universität Berlin（柏林工业大学）； Northern Arizona University（北亚利桑那大学）

作者：Yue Xia, Tayyebeh Jahani-Nezhad, Mayank Bakshi, Rawad Bitar

英文摘要：We consider federated parameter efficient fine-tuning of large neural networks with low-rank adaptation (LoRA,~Hu et al.\ 2022). Combining LoRA with federated PEFT introduces challenges absent from either setting alone: clients may use different LoRA ranks, making their factor matrices dimension-incompatible, and factor-wise averaging suffers from a bilinear mismatch. We propose SeFoRA, a sketch-aggregated federated LoRA algorithm in which each client transmits a linear sketch of its local updates, enabling direct aggregation at the federator. As a result, SeFoRA alleviates the bilinear mismatch, and allows for aggregation in a small subspace of the full model. We introduce a rank-homogeneous version called SeFoRA-Ho which allows for direct adapter aggregation in this setting. We prove convergence to a neighborhood of the first-order stationary point at rate $\cO(1/T)$ for the rank-homogeneous setting. Numerical experiments on fine-tuning RoBERTa-Large on GLUE datasets show how our algorithms outperform the state-of-the-art.

AI 总结：MERA以单模型调用为适应单元，通过多轮适配提升小模型能力，结合带验证器回退的成本校准路由，在HumanEval+MBPP、TAU-2等数据集上实现小模型性能提升与成本降低。

链接：https://arxiv.org/abs/2608.10333

机构：Gradient； Soochow University（苏州大学）； Carnegie Mellon University（卡内基梅隆大学）； Shanghai Jiao Tong University（上海交通大学）； University of California, Los Angeles（加利福尼亚大学洛杉矶分校）

作者：Yuhang Yao, Zeyu Wang, Wanyi Chen, Tongyun Yang, Yuhang Han, Jie Xiao, Chengke Bao, Tianyi Zhao, Lynn Ai, Eric Yang, Tianyu Shi

英文摘要：LLM agents execute heterogeneous sequences of model calls within a single task: some invocations require careful reasoning, while others are structured steps such as formatting or tool-argument construction. Prior routing methods exploit this asymmetry by assigning easy invocations to a cheaper small model and difficult ones to a large model. Such policies reduce inference cost, but they leave the small model's capability unchanged, so attainable savings remain bounded by the work the student can already solve. MERA instead improves the small model itself, using a single model invocation as the unit of adaptation. In each cycle, MERA replays failed student invocations to obtain execution-verified teacher demonstrations, distills recurring procedures into an iteratively updated SkillBook, and fine-tunes a student LoRA adapter via supervised learning and optional GRPO. Routing serves as supporting machinery for deployment: the improved student is served behind a cost-calibrated router with verifier-backed fallback, and a candidate SkillBook, adapter, or router is admitted only when joint replay preserves task quality. Empirically, four-cycle adaptation raises Qwen2.5-Coder-1.5B from 28.7% to 49.7% pass on held-out HumanEval+MBPP. Under verifier-backed fallback, the deployed policy retains 88.3% pass at 60.8% of always-Luna cost. On TAU-2, a fine-tuned Qwen3.5-2B improves from 14/35 to 18/35 and matches an unadapted 4B model. These results indicate that verifier-backed multi-cycle adaptation can increase small-model capability, rather than only routing around a fixed student.

AI 总结：该研究提出Latent Critic轻量级LoRA适配器，可实时检测LLM智能体的幻觉，定位准确率超80%、AUROC达0.966，能拦截幻觉并助力智能体自我修正，效能优于同类基线方法。

链接：https://arxiv.org/abs/2608.10430

机构：Samsung Research America（美国三星研究院）

作者：Sanidhya Vijayvargiya, Rahul Lokesh

英文摘要： Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures, executing hallucinated, undesired actions to force a resolution rather than expressing uncertainty. Existing detection methods fail to provide actionable, real-time correction as they either do not localize the hallucinations, or incur prohibitive inference latency. We introduce the Latent Critic, a lightweight low-rank adapter (LoRA) that operates concurrently with a frozen base LLM's generation to actively restructure the transformer's residual stream---amplifying latent grounding signals and translating them into localized, natural language feedback within a single sequence. By refining the base model's native uncertainty signals, this manipulation of the latent space enables reliable, granular detection without the overhead of secondary inference loops. Mechanistic analysis via activation patching and layer-wise probing shows that this rank-invariant behavior restructures pre-existing uncertainty geometry into a linearly separable representation that transfers more reliably than base model representations alone. Using tool-calling as an instantiation of granular hallucinations, we validate the detection and downstream improvements enabled by the Latent Critic architecture across Qwen and Llama-based models. Demonstrating superior real-time efficacy, our approach significantly outperforms equivalent-scale fine-tuned external detectors, semantic entropy baselines, and passive internal probes in isolating hallucinations, achieving 0.966 AUROC and >80% accuracy in localization (e.g., ungrounded: date). When deployed in a closed-loop ReAct environment, the Critic acts as a negligible latency guardrail, intercepting hallucinations before execution to prevent undesired actions while simultaneously leveraging this specific localized feedback to enable efficient agent self-correction.

AI 总结：本研究提出Diffract工具包，通过分析持续预训练的大语言模型的权重矩阵奇异值谱，发现可选择性回退低重要性注意力头以提升领域适配性能，实现高效的领域自适应。

链接：https://arxiv.org/abs/2608.10850

作者：Nikita Borodin, Maria Krylova, Artem Zabolotnyi, Dmitry Aspisov, Egor Shikov, Nikita Tyuplyaev, Oleg Travkin, Roman Alferov, Dmitry Vinichenko

英文摘要：We study continual pre-training (CPT) as a mechanism for adapting general-purpose large language models to specialized domains: mathematics, instruction, code, and natural text. Using singular value decomposition of weight matrices, we find that CPT leaves singular value spectra largely invariant, with adaptation driven mainly by changes in singular vectors. An analysis of attention-head projection matrices reveals strong, domain-dependent head heterogeneity, which we exploit to define a head importance criterion: up to 60% of head updates can be removed without measurable quality loss. Selectively rewinding low-importance heads to their pre-trained state improves benchmark accuracy by up to 4% versus the fully trained baseline. Finally, we identify domain connectivity - linear interpolation between CPT checkpoints yields smooth domain-quality interpolation without notable degradation on either domain - and release Diffract, an open-source toolkit for scalable spectral analysis of billion-parameter models.

AI 总结：UserToolBench是针对工具使用类大语言模型的基准测试集，可评估模型从交互历史推断用户偏好等个性化决策能力，实验发现当前模型在多工具协调等方面仍存瓶颈。

链接：https://arxiv.org/abs/2608.10042

机构：Sun Yat-Sen University（中山大学）； Nanyang Technological University（南洋理工大学）

作者：Xuexiong Yin, Zechuan Chen, Yongsen Zheng, Yuxiang Zhang, Jingyuan Yang, Bin Wang, Yubin Wang, Keze Wang

英文摘要：Tool-use LLMs are increasingly asked to act on users' behalf, but existing benchmarks usually focus on profile recall, style imitation, generic tool use, or response-level personalization. We introduce UserToolBench, a benchmark for personalized decision making in tool-use LLMs. UserToolBench tests whether a model can infer latent user preferences from interaction history, recognize when clarification is needed, and produce user-aligned tool-call trajectories under incomplete information. The benchmark is built from privacy-sanitized real interaction traces and combines structured persona profiles, public API-style tool ecosystems, and long-horizon multi-turn trajectories. It includes 10 user profiles, 36 tool sets, 1,065 turns, 170 unique tools, and evaluation-focused task types covering lack-of-information, single-tool, and multi-tool settings. Experiments with strong tool-use LLMs show that current models still have difficulty with personalized delegation. Multi-tool coordination, missing-constraint inference, and long-horizon behavioral consistency remain major bottlenecks. These results suggest that personalization evaluation should move beyond asking whether outputs sound user-specific and instead ask whether LLMs make correct decisions for the users they represent.

AI 总结：该研究开发了首个经专家验证的人权基准HumRightsBench，调整IRAC框架为IRAP，通过真实场景测试LLMs的人权推理能力，发现模型准确率差异显著，可推动AI评估科学发展。

链接：https://arxiv.org/abs/2608.10268

作者：Savannah Thais, Wm. Matthew Kennedy, Abhigyan Acherjee, Matilda Wysocki, Malcolm Langford, Caitlin Kraft Buchman

英文摘要：Large language models (LLMs) increasingly mediate legal determinations over what human rights are realized, and how. Yet, no evaluation benchmark exists to assess whether they can reason correctly about human rights law. To this end, we report our efforts to develop a robust and scalable methodology for creating HumRightsBench: the first expert-validated, scenario-based benchmark for evaluating reasoning grounded in the obligation structure of international human rights law. We adapt the IRAC framework for legal reasoning to better suit the unique reasoning patterns of human rights work (substituting P, "proposing remedies," for C, "legal conclusion," yielding IRAP) to structure our evaluation heuristics. We also produce a pilot series of authentic scenarios designed to implicate the many dimensions of real-world human rights issues and annotated by human rights lawyers and professionals across the world. Ultimately, we find that model accuracy scores range considerably across legal reasoning tasks (overall model performance ranges from 0.339 to 0.577, task min-max ranges from 0.025 to 0.774), which strongly implies that HumRightsBench is a capable instrument for advancing this emerging subfield of AI evaluations science at a critical moment in its evolution.

AI 总结：该研究针对隐私敏感时间序列预测场景，通过TSTR协议构建基准测试，提出Grasynd-P方法，揭示不同生成方法的预测与隐私权衡，为隐私感知合成时间序列生成方法提供评估参考。

链接：https://arxiv.org/abs/2608.10891

机构：University of Minho（米尼奥大学）； Universidade do Porto（波尔图大学）； Laboratory for Artificial Intelligence and Computer Science (LIACC)（人工智能与计算机科学实验室（LIACC））； Fraunhofer Portugal AICOS（弗劳恩霍夫葡萄牙AICOS机构）； INESCTEC； University of Coimbra（科英布拉大学）

作者：Luis Amorim, Vitor Cerqueira, Moises Santos, Paulo J. Azevedo, Carlos Soares

英文摘要：Time series forecasting in privacy-sensitive domains often requires training models on released data rather than original observations. Synthetic time series generation has been developed primarily for data augmentation, where generated series supplement the original training set. How well these methods perform when fully replacing the original data - and how much privacy risk the released series carry - remains underexplored. We address this gap through a benchmark evaluating synthetic generation methods and noise-based anonymization baselines under a Train on Synthetic, Test on Real (TSTR) protocol. We jointly assess forecasting performance and distance-based empirical privacy risk across seven datasets, characterizing the trade-off between these objectives. We also introduce Grasynda-P, a privacy-motivated extension of the graph-based generator Grasynda, incorporating matrix ensembling and kernel density estimation. Our results show that: (1) no generation method fully substitutes for original training data; (2) noise-based anonymization yields the strongest privacy but the worst forecasting performance; (3) simple transformation-based generators outperform deep generative models for forecasting in this setting; and (4) Grasynda-P lies on the Pareto frontier, achieving competitive forecasting with stronger privacy separation than other generators. This benchmark establishes a reference point for evaluating and developing new privacy-aware synthetic time series generation methods.

AI 总结：提出PhysDGM模型，将物理规则嵌入扩散生成过程以合成符合物理定律的工业时间序列，构建的440万样本数据集可提升下游任务性能并减少数据需求，助力数据稀缺环境的AI应用。

链接：https://arxiv.org/abs/2608.10941

机构：Beihang University（北京航空航天大学）； The Hong Kong Polytechnic University（香港理工大学）

作者：Haiteng Wang, Yunfei Zhu, Tao Wang, Yikang Li, Jiabao Dong, Xiaoge Zhang, Lei Ren

英文摘要：Industrial time-series signals, such as turbine temperature and rotational speed in aero-engines, are essential for monitoring the health and operational status of complex dynamical systems. However, collecting such data is often limited by harsh environments (e.g., high temperature and high pressure) and the high cost of experimental testing. To address this challenge, we introduce PhysDGM, a stepwise physics-embedded diffusion generative model for synthesizing time-series data that are consistent with the underlying physical laws of dynamical systems. PhysDGM embeds physical laws directly into each reverse diffusion step of the generative process, ensuring trajectory-level physical consistency, rather than enforcing constraints only at the final output. A large-scale AI-synthetic dataset (4.4 million samples, 20x scale-up) constructed by PhysDGM demonstrates strong fidelity across 34 datasets spanning turbofan engines, aero-engines, batteries, and chemical processes. After incorporating the synthetic data, the downstream task performance substantially surpassed that using real data alone by 48% for remaining useful life prediction, 15% for health indicator estimation, 22% for state-of-health assessment, and 20% for fault diagnosis. Moreover, it requires 10-20x less training data than existing approaches, substantially reducing the high cost of data collection in dynamical systems. We further demonstrate PhysDGM's potential in identifying early-stage faults in aero-engines by incorporating AI-synthesized data. In summary, PhysDGM provides a solid foundation for generating physically consistent industrial time-series, paving the way for expanding physics-guided AI into diverse data-scarce environments, including both industrial machinery and complex chemical reaction dynamics.

AI 总结：本综述梳理跨视图特征匹配领域进展，构建结构化分类体系，开展统一基准测试，提炼设计原则，探讨开放挑战，为该领域发展提供全面参考。

链接：https://arxiv.org/abs/2608.11093

机构：School of Automation, Southeast University（东南大学自动化学院）； School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）； Institute of Artificial Intelligence, University of Science and Technology Beijing（北京科技大学人工智能研究院）； School of Robotics, Wuhan University（武汉大学机器人学院）； Graduate School of Information, Production and Systems, Waseda University（早稻田大学信息生产系统研究科）

作者：Songlin Du, Xiaoyong Lu, Zeyu Wu, Xiaobo Lu, Guobao Xiao, Bin Fan, Jiayi Ma, Takeshi Ikenaga

英文摘要：Cross-view feature matching aims to establish reliable correspondences across images with large viewpoint variations. Over the past decade, the field has evolved from task-specific models toward increasingly unified and generalizable correspondence models, with recent progress further driven by the emergence of vision foundation models (VFMs). Despite these advances, existing studies remain highly diverse in their problem formulations, model architectures, training paradigms, and evaluation protocols, making it difficult to obtain a unified understanding of the field. In this survey, we present a unified review of cross-view feature matching. We first introduce a structured taxonomy covering feature extraction, single-type feature matcher, multi-type feature matcher, VFMs based methods, training strategy and robust estimation, providing a coherent framework for analysis and comparison. We further examine recent advances, distilling key design principles and highlighting the shift toward unified and generalizable correspondence models. We also provide a unified experimental benchmarking of representative state-of-the-art methods under consistent protocols, enabling fair and comprehensive performance comparisons. In addition, we discuss open challenges and future directions, including efficiency, robustness under extreme conditions, and cross-domain generalization. This survey aims to provide a comprehensive and structured reference for understanding the evolution, current landscape, and future development of cross-view feature matching in the era of vision foundation models.

AI 总结：本研究提出一种基于EM算法的方法，联合学习成对比较场景下的物品奖励与工作者可靠性，通过Polya-Gamma潜变量优化模型，在真实与合成数据集上验证了其对垃圾工作者的强鲁棒性。

链接：https://arxiv.org/abs/2608.10045

机构：IIT Bombay（印度理工学院孟买分校）

作者：Kaustubh Shivshankar Shejole, Tanish Agarwal, Arpit Agarwal, Avishek Ghosh

英文摘要：The problem of learning from pairwise comparisons has been widely studied across many domains such as recommendation systems, social choice, and more recently, fine-tuning large language models. In this problem, the goal is to learn item rewards based on pairwise comparisons between them. In many scenarios, these comparisons are elicited from crowdworkers using platforms such as Amazon Mechanical Turk, Scale AI, etc. However, crowdworkers are often unreliable due to limited domain knowledge or revenue-maximizing (spamming) behavior. In this work, our goal is to understand whether worker reliability (competency) can be learned jointly with item rewards. To this end, we adopt the Boltzmann-rational model for pairwise comparisons, which extends the Bradley-Terry-Luce model by incorporating worker competencies. We derive an EM-based algorithm for learning under this model by introducing Polya-Gamma latent variables to transform the logistic likelihood into a conditionally Gaussian form, enabling tractable optimization and leading to a simplified $Q$ function in the E-step of the algorithm. This technique allows us to reduce our formulation to a matrix sensing problem, using which we establish theoretical convergence guarantees for our algorithm. We conduct extensive experiments on real-world and synthetic datasets. These experiments demonstrate the advantages of using our algorithm over several baselines and confirm its strong robustness to both spammers and adversarial workers, highlighting its practical effectiveness in realistic crowdsourcing and reward learning settings. The code and data is publicly available at this https URL.

AI 总结：该研究针对单一时间序列预测模型的局限性，提出基于LLM推理的REATS集成方法，通过三方面设计实现样本自适应可解释加权，在八个基准测试上优于竞争基线，具备强泛化与迁移能力。

链接：https://arxiv.org/abs/2608.10149

机构：Fudan University（复旦大学）； Microsoft Research（微软研究院）； Nankai University（南开大学）； Jilin University（吉林大学）

作者：Xu Zhang, Chang Xu, Hui Sun, Nan Ma, Zijian Zhang, Peng Wang, Wei Wang, Li Zhao

英文摘要：Due to the diversity of real-world time series, no single forecasting model consistently dominates across all samples. Ensemble learning addresses this by combining complementary model strengths, yet existing methods rely on fixed rules or black-box models based solely on numerical inputs, failing to leverage LLM reasoning for interpretable weighting decisions. We propose REATS, which leverages LLM reasoning capabilities as an intelligent ensemble router that jointly processes textual temporal pattern descriptions and numerical features to produce interpretable, sample-adaptive ensemble weights through chain-of-thought reasoning. To enable effective LLM-based ensembling, we study its key design choices and propose: (i) a structured input pipeline that transforms raw time series into hybrid textual--numerical representations with fixed token cost, enabling rule-based chain-of-thought construction without API dependency, augmented with retrieved similar-sample priors; (ii) a diverse multi-row weight supervision scheme coupled with a token-efficient percentage-table format that reduces numerical complexity and mitigates LLM hallucinations; and (iii) a two-stage fine-tuning framework combining SFT with GRPO, where a reciprocal reward mapping transforms the continuous unbounded MSE gap into bounded signals with amplified near-oracle sensitivity, addressing the uniform sensitivity and outlier-dominated advantage compression inherent in naive reward designs for regression-based GRPO. Experiments on eight benchmarks demonstrate that REATS outperforms competitive ensemble baselines while providing natural language explanations and demonstrating strong transfer learning and out-of-domain generalization to unseen candidate models.

AI 总结：该研究针对大规模定向投放与推荐系统的资源错配问题，提出以决策为中心的因果优化框架，经实验验证可实现主要长期价值指标7.20%的统计显著提升，证明了生产规模因果优化的可行性。

链接：https://arxiv.org/abs/2608.10182

机构：LinkedIn（领英）

作者：Changshuai Wei, John Bencina, Phuc Nguyen, Andre Assuncao Silva T Ribeiro, Benjamin Zelditch

英文摘要：Large-scale targeting and recommendation systems are typically built around predictive scores fed into heuristic or local allocation. When the business goal is incremental impact, as in marketing campaigns, incentives, and notifications, this paradigm systematically misallocates resources toward users who would have acted anyway. We present a decision-centric framework that instead optimizes causal effects under global constraints, aligning three components under a single objective: a causal neural network with a Transformer backbone for individual treatment-effect estimation, a Bayesian neural-bandit layer for uncertainty-aware exploration, and a dual-based large-scale linear-programming layer for constrained allocation. The framework also supports sequential context and multi-outcome, attribute-conditioned scoring through a Transformer encoder and outcome embeddings. We evaluate it with offline simulations on a public bandit dataset, targeted architectural ablations, and an online A/B test on LinkedIn Feed marketing traffic. We also distill production lessons on causal training-data construction and cost and delivery control, which were critical to successful deployment. The end-to-end treatment policy delivered a statistically significant $+7.20\%$ lift in the primary long-term-value metric, demonstrating the feasibility of production-scale causal optimization under business constraints.

AI 总结：该研究提出STCAD框架，通过自定义BERT模型与CURE层次聚类实现TB级AIS轨迹的无监督聚类，结合重构损失与聚类噪声分配检测异常，在国家级AIS数据集上验证了方法的有效性。

链接：https://arxiv.org/abs/2608.10249

作者：Bertram Hage, Alexander Schiøtz, Felix Thomsen, Christian Rand, Peder Heiselberg

英文摘要：We present a scalable framework for unsupervised clustering of maritime trajectories derived from terabyte-scale Automatic Identification System (AIS) archives. Variable-length trajectories are encoded with a custom BERT-based model trained via masked token modeling and clustered using CURE hierarchical clustering, producing physically interpretable trajectory groups without requiring a predefined number of clusters. An intrinsic unsupervised anomaly detection method based on reconstruction loss and clustering noise assignment identifies irregular navigation patterns. The framework is demonstrated on a national-scale AIS dataset comprising billions of messages spanning one year, yielding stable trajectory clusters and a clear separation between nominal and anomalous vessel behavior.

AI 总结：针对船舶轨迹预测的地理偏差与真实性问题，提出CRHT框架，结合在线K-means聚类采样与混合架构，在短期预测中表现最优，平衡了精度与机动跟踪能力。

链接：https://arxiv.org/abs/2608.10256

作者：Alexander Schiøtz, Bertram Hage, Christian Rand, Felix Thomsen, Peder Heiselberg

英文摘要：Accurate vessel trajectory prediction is critical for maritime safety and anomaly detection, yet existing models often struggle with geographic bias and navigational realism. We propose the Continuous Regression Hybrid Transformer (CRHT), a deep learning framework designed to forecast vessel motion using Automatic Identification System (AIS) data. To mitigate spatial data imbalance, we introduce an online K-means cluster sampling strategy that ensures diverse exposure to rare maneuvers during training. Our hybrid architecture integrates 1D convolutional layers for local kinematic feature extraction with a multi-head attention mechanism for global temporal context. CRHT demonstrates superior performance in short-term forecasting, achieving the lowest errors at the 1-hour horizon. The results demonstrate that while discrete models provide high navigational stability over long horizons, CRHT offers an optimal balance of precision and maneuver tracking for real-time maritime surveillance.

AI 总结：本文提出RCCP方法，通过选择相似过去残差为局部证据并修正检索导致的覆盖率误差，在时间序列预测中实现目标覆盖率、低失误与开销，提升不确定性量化效果。

链接：https://arxiv.org/abs/2608.10553

机构：Ulsan National Institute of Science and Technology（蔚山科学技术院）； LinqAlpha（林克阿尔法）

作者：Sangjin Jin, Kangmin Kim, Junhyeong Lee, Yongjae Lee

英文摘要：Conformal prediction (CP) provides distribution-free prediction intervals for fixed forecasters, but its standard calibration procedure is often inefficient for time series data, where forecast errors are temporally dependent and change across time and operating conditions. Recent time series CP methods improve local calibration using recent, weighted, or localized residuals. Yet local calibration can remain indirect, since broad residual weighting or additional adaptation procedures may dilute the evidence most relevant to the current prediction. This motivates a simple retrieval and correction strategy that selects similar past residuals as local evidence and then corrects the coverage error left by retrieval. In this paper, we propose Retrieval--Corrected Conformal Prediction (RCCP), a retrieval-augmented calibration method for time series prediction intervals. RCCP builds an asymmetric interval from retrieved one-sided residuals and calibrates its normalized retrieval error with a scalar conformal correction. Thus, retrieval provides local residual evidence, while conformal correction determines the final scale needed for coverage. We provide a coverage-gap bound based on the stability of the normalized retrieval error distribution. Across standard benchmarks and backbone forecasters, RCCP attains the target coverage in every setting and achieves the lowest Winkler scores, with fewer severe misses. RCCP also achieves low calibration and inference overhead, showing that retrieval-corrected calibration is an effective and scalable approach to uncertainty quantification in time series forecasting. Code is available at this https URL.

AI 总结：该研究针对现有异常诊断方法的缺陷，提出可扩展的基线参考诊断方法BREAD，经数学保证和实验验证，其诊断结果比LIME更忠实准确，适用于AI前瞻性异常检测场景。

链接：https://arxiv.org/abs/2608.10587

机构：University of Amsterdam（阿姆斯特丹大学）； Amsterdam Business School（阿姆斯特丹商学院）

作者：Jiaqi Qiu, Rob Goedhart, Jannis Kurtz, Inez M. Zwetsloot

英文摘要： Artificial Intelligence (AI)-based prospective anomaly detection methods are increasingly deployed in high-dimensional and nonlinear settings. Among these approaches, AI-based statistical process monitoring (SPM) is widely used, providing a structured framework for prospective monitoring. Once an anomaly is detected, a diagnosis method is needed to identify the features driving the flagged observation away from normal behaviour. Traditional SPM diagnosis methods are typically designed for specific detection models and cannot be directly applied to AI-based methods. Model-agnostic explainable AI (XAI) offers a general framework for feature relevance explanation. However, existing methods suffer from scalability limitations or assign relevance to noise features, reducing diagnosis accuracy. We propose a scalable, baseline-referenced diagnosis method that uses both the anomalous observation and normal baseline information. We provide mathematical guarantees that under a mean-shift anomaly setting, the proposed method achieves higher faithfulness in detecting the features causing the anomaly compared to LIME. Simulation studies and a real-world case study validate the effectiveness of the proposed method and show that it generates more faithful and accurate diagnosis results for AI-based prospective anomaly detection methods.

AI 总结：本文提出ProTAGAD基础模型，通过解耦拓扑与文本原型构建双原型库，缓解传统方法的异常边界模糊问题，在14个基准数据集的跨域场景中实现最先进TAG异常检测性能。

链接：https://arxiv.org/abs/2608.10699

作者：Ziyan Wang, Liwen Wu, Cheng Xie, Song Gao, Zhenli He, Xin Jin

英文摘要：Text-Attributed Graphs (TAGs), endowed with abundant textual content along with topological structures, have emerged as a versatile backbone for real-world anomaly detection spanning large language model security, social network moderation, and cyber threat identification. Unlike conventional Graph Anomaly Detection (GAD), which relies primarily on structural irregularities, TAG anomaly detection must jointly leverage both topological patterns and fine-grained textual semantics to capture nuanced anomalous behaviors. The current GNN-based anomaly detectors adopt holistic message-passing schemes that indiscriminately fuse structural proximity and textual semantics during propagation, leading to deep cross-modality coupling. This entanglement acts as a noise amplifier, obscuring subtle anomalous signals and directly giving rise to the Blurred-Anomaly-Boundary (BAB) issue by rendering normal-anomalous decision boundaries poorly separable. This challenge is further amplified for graph foundation models that require robust cross-domain generalization. To bridge this gap, we introduce a novel foundation model for TAG anomaly detection featuring decoupled topological and textual prototypes. Our framework constructs dual prototype banks to independently model structural normality and semantic consistency, effectively isolating anomaly cues that are otherwise diluted during coupled aggregation. Extensive experiments across 14 diverse benchmark datasets demonstrate that our method consistently achieves state-of-the-art performance in cross-domain settings. Notably, the ablation studies further corroborate the prevalence of the BAB issue in conventional coupled TAG anomaly detectors, and show that our decoupled prototype design effectively mitigates this challenge.

AI 总结：该研究对比PINNs中FD与AD的导数计算性能，发现FD精度相当且速度更快、内存占用更少，其随机变体在稳态问题上优于AD，还解决了含样本间依赖架构的逐样本导数计算问题。

链接：https://arxiv.org/abs/2608.11020

机构：AGH University of Krakow（克拉科夫AGH科技大学）

作者：Maciej J. Mikulski, Tadeusz Uhl

英文摘要：We systematically investigate finite-difference (FD) derivative computation in Physics-Informed Neural Networks (PINNs) as an alternative to automatic differentiation (AD). On three benchmark PDEs we show that, with a properly calibrated step size, FD matches AD in accuracy on every problem while running faster across the full tested batch-size range and using substantially less GPU memory, and that a stochastic variant we propose outperforms AD on a stationary problem. We further show that for neural architectures with inter-sample dependencies (e.g. BatchNorm, self-attention) the standard PyTorch autograd idiom is silently incorrect; the correct per-sample alternative is computationally infeasible at PINN-relevant batch sizes, while FD provides a forward-only approximation that is empirically an order of magnitude closer to the true per-sample derivative.

AI 总结：该研究针对内存受限的推荐系统训练，分析固定内存预算下批量大小与负样本数量的权衡，提出优先扩大批量的选择规则，经实验验证可提升收敛速度与推荐质量。

链接：https://arxiv.org/abs/2608.11061

机构：Moscow Independent Research Institute of Artificial Intelligence（莫斯科独立人工智能研究院）； Intellectual data analysis and predictive modeling institute（智能数据分析与预测建模研究院）； Applied AI Institute（应用人工智能研究院）； Risk department（风险部门）

作者：Artyom Sabitov, Daniil Volkov, Alexey Zaytsev

英文摘要：Large-scale neural recommender systems are typically trained with a softmax cross-entropy objective over the full item vocabulary. For a typical large number of possible items $K$, the final classification layer dominates memory, requiring $O(nK)$ logits and gradients to materialize for a batch of $n$ examples. Sampled softmax reduces this cost by restricting the objective to only $k \ll K$ candidate negative items, resulting in an $O(nk)$ memory. However, for a fixed budget $B = n k$, it remains unclear whether one should prioritize larger batches or the inclusion of more negative items. We address this question by analyzing sampled-softmax training under a fixed memory constraint. Under standard smoothness and variance assumptions, our theoretical evidence suggests that the fastest convergence arises from an $ n \sim B, k \sim 1$ allocation. So, an actionable rule is to include as many objects as possible given computational constraints. Our theory is supported by controlled synthetic and synthetic and four real sequential recommendation benchmarks, including MovieLens-20M. The suggested configuration achieve faster convergence and better final recommendation quality than imbalanced alternatives within the same memory constraint. These findings provide a theoretical and empirical foundation for configuring memory during the training of recommender systems. Code, reproducibility materials, and all scripts for generating figures are available at this https URL

AI 总结：针对概率预测中分布灵活性与均值准确性的权衡，提出两阶段奇数残差流框架，解耦均值预测与不确定性估计，在长短时域预测中同时实现最优确定性精度与出色密度估计性能。

链接：https://arxiv.org/abs/2608.11114

作者：Kiran Madhusudhanan, Christian Klötergens, Lars Schmidt-Thieme, Vijaya Krishna Yalavarthi

英文摘要：Probabilistic forecasting plays an essential role in risk-sensitive decision-making, particularly in long-horizon settings. However, existing approaches often face a fundamental trade-off between distributional flexibility and accurate mean prediction. Traditional parametric methods, such as Mean Variance Estimation (MVE), can suffer from degraded point accuracy when trained under joint Negative Log-Likelihood (NLL) objectives, while modern-flexible generative models, including Normalizing Flows and Diffusion Models, typically rely on costly Monte Carlo sampling and may yield suboptimal mean estimates. To address this limitation, we propose Two-stage Odd Residual Flows (TORF), a framework that decouples mean forecasting from uncertainty estimation. In the first stage, a pre-trained deterministic model is used to produce an accurate mean prediction. In the second stage, a Restricted Normalizing Flow, with strictly odd functions learns flexible residual distributions around the point forecast, guaranteeing mean preservation from the first stage without sampling. Experiments show that TORF achieves state-of-the-art deterministic accuracy (NMAE) while providing strong density estimation performance (CRPS) on short and long-horizon forecasting.

AI 总结：本文针对现有基于RSSI的传感器子集选择方法易受声学干扰的问题，提出结合频带声学特征与双塔MLP架构的推荐系统框架，在户外车辆跟踪任务中较RSSI基线提升约20%精度且保持低计算开销。

链接：https://arxiv.org/abs/2608.11143

机构：University of California, Los Angeles（加利福尼亚大学洛杉矶分校）

作者：Kaan Buyukkalayci, Kyle Pak, Merve Karakas, Christina Fragouli

英文摘要：This paper develops a method for sensor-subset selection for tracking. Prior work showed that low-cost acoustic Received Signal Strength Indicator (RSSI) measurements can be used to recommend subsets of sensor nodes whose expensive sensing modalities, such as cameras, can achieve high tracking accuracy. While efficient, RSSI-based approaches are challenged by acoustic interference. We propose a recommendation-system-inspired framework that instead leverages frequency-band acoustic features and a Two-Tower Multi-Layer Perceptron (MLP) architecture to efficiently score candidate sensor subsets. Experimental results on outdoor vehicle-tracking deployments show that the proposed method can improve accuracy by around 20\% over the RSSI baseline while maintaining the low computational overhead required for real-time selective sensing.

AI 总结：该研究针对Transformer可解释性研究中表示演变分析的不足，提出基于持续同调的Transformer几何观测站TGO-IV拓扑框架，通过多种拓扑工具全面分析表示点云的全局拓扑演变。

链接：https://arxiv.org/abs/2608.09997

作者：Kaustubh Kapil, Kishor P. Upla

英文摘要：Transformers have had a profound impact on the world of language processing and computer vision. As efforts to answer the million-dollar question of ``How does a Transformer learn?" have been increasing, existing interpretability studies primarily analyze representations at isolated layers or the network as a whole, while the developmental evolution of individual representations and its manifolds across transformer layers remains underexplored. With this work, we aim at providing a comprehensive analysis of the evolution of representations as the representation point cloud transforms across the layers; thereby attempting to isolate layers or establish a trend which comes closer to justifying how and when raw input representations evolve into task-relevant feature representations. Thus, Transformer Geometry Observatory-TGO-IV introduces a topological framework for analysing the evolution of Transformer representations through the lens of Persistent Homology. Rather than studying local geometric properties alone, TGO-IV constructs Vietoris--Rips simplicial complexes from token-level representation point clouds and investigates the evolution of their persistent topological signatures across Transformer layers. The proposed framework comprises complementary topological observatories including Persistence Diagrams, Barcode Diagrams, Betti Curves, Persistence Landscapes, Bottleneck Distance, and Wasserstein Distance, enabling a comprehensive analysis of how the global topology of representation point clouds develops throughout the forward pass.

AI 总结：针对现有深度随机神经网络对噪声/异常值鲁棒性不足的问题，提出IF-dRVFL与IF-edRVFL框架，通过直觉模糊理论分配样本自适应权重，在UCI、KEEL数据集上的实验验证了其性能优于现有SOTA方法。

链接：https://arxiv.org/abs/2608.10007

机构：Indian Institute of Technology Indore（印度印多尔印度理工学院）； Qatar University（卡塔尔大学）

作者：M. Sajid, A. Quadir, A. Rahaman, P. N. Suganthan, M. Tanveer

英文摘要：The current state-of-the-art (SOTA) deep randomized neural networks, such as deep Random Vector Functional Link (dRVFL) and ensemble deep RVFL (edRVFL), treat all training samples uniformly, which limits their robustness and effectiveness when applied to real-world datasets containing noise and outliers. Furthermore, the propagation of contaminated features across hidden layers negatively influences the decision-making capability of these models. To overcome these limitations, we propose intuitionistic fuzzy dRVFL (IF-dRVFL) and intuitionistic fuzzy edRVFL (IF-edRVFL) frameworks that enhance model robustness. The proposed models unify intuitionistic fuzzy theory to exploit sample neighborhood information in the kernel space by jointly considering membership and non-membership degrees for each sample. Membership degrees are computed based on the distance of samples from their respective class centroids, while non-membership degrees quantify sample heterogeneity within local neighborhoods. These measures are employed to assign adaptive weights to training samples, enabling effective discrimination among clean, noisy, and outlier data points. Extensive experiments conducted on UCI and KEEL benchmark datasets, with and without the presence of Gaussian noise, demonstrate the superiority of the proposed IF-dRVFL and IF-edRVFL models over existing SOTA fuzzy and non-fuzzy approaches. The source code is available at this https URL.

AI 总结：本文提出CurveFP数据类型，通过闭包乘积算术协同设计，在少1位元素位数下提升语言模型性能，降低运算误差，优于FP8且更适合紧凑部署。

链接：https://arxiv.org/abs/2608.10010

机构：University of California, Irvine（加州大学欧文分校）

作者：Ye Qiao

英文摘要：Low-precision datatypes reduce language-model cost, but most formats optimize scalar fidelity while leaving the arithmetic induced by their products unchanged. We introduce CurveFP, a closed-product codebook family that distributes quantized magnitudes across interleaved logarithmic curves under compact block scales. A rational radix tunes dynamic range against local resolution, while uniform curve indices make every nonzero product algebraically closed. Product formation becomes an exact sign XOR and integer-index update, and a derived finite phase count determines the accumulation schedule. We instantiate this algebra as CurveFP eight E4C3/E5C2 for training and CurveFP seven E3C3 for compact deployment. In evaluation, CurveFP seven beats tensor-wise FP8 perplexity on four 7B--9B models with one fewer element bit and stays within 1.32\% of native quality. CurveFP eight lowers operand NMSE in all 36 paired forward and backward GEMM comparisons. Across three matched 128.3M-parameter triplets, every mode completes 3B-token pretraining per seed; CurveFP eight reaches mean BF16-inference perplexity 22.5366 versus 22.5407 for FP8 and incurs a lower format-induced penalty in all three seeds. A 36-cell downstream matrix finds lower WikiText-103 perplexity for the CurveFP eight-trained checkpoints in all 12 seed-format comparisons, with mixed PG-19 and task deltas. Together, these results establish CurveFP as an arithmetic co-design that combines FP8-class numerical behavior, seven-bit inference, and a substantially simpler product path.

AI 总结：该研究针对LLM智能体工具文档的异质性与泛化问题，提出DocsChisel自适应优化框架，经实验较原始文档及EasyTool、DRAFT基线大幅提升任务成功率，且开销有限。

链接：https://arxiv.org/abs/2608.10037

作者：You Lu, Kun Zhang, Bihuan Chen, Xin Peng

英文摘要：Large language models (LLMs) increasingly rely on external tools to accomplish complex real-world tasks, making tool documentation a critical grounding resource for LLM agents. Existing studies mainly focus on improving the tool-use capabilities of LLM agents, while largely treating tool documentation as a fixed input. Although several recent works attempt to optimize tool documentation through rewriting or compression, little is known about how the information contained in tool documentation affects agent performance across different settings. To bridge this gap, we conduct a large-scale empirical study on tool documentation for LLM agents. Our study reveals substantial heterogeneity in the information fields provided by existing tool documentation. Moreover, the effectiveness of different information fields is highly dependent on the task domain, LLM backbone, and agent paradigm, indicating that no fixed tool documentation can consistently generalize across diverse agent settings. Motivated by these findings, we propose DocsChisel, an adaptive tool documentation optimization framework for LLM agents. DocsChisel analyzes failed execution traces of a target LLM agent to identify documentation-related issues, and iteratively optimizes tool documentation by adding, removing, and refining information fields for each tool. We evaluate DocsChisel against two state-of-the-art baselines, i.e., EasyTool and DRAFT. Experimental results show that DocsChisel improves the task success rate of LLM agents by 95.89% over the original tool documentation and by 75.15%, on average, over existing baselines, while incurring limited optimization time and token overhead

AI 总结：FlowScout是从历史任务记录生成工具集成型智能体工作流的执行引导框架，经多任务域评估，其工具调用正确性与执行质量均显著优于PM4Py等基线方法。

链接：https://arxiv.org/abs/2608.10039

作者：Shuo Hao, You Lu, Bihuan Chen, Xin Peng

英文摘要： Agentic workflows have become an important abstraction for building reliable LLM-based automation systems by organizing large language models (LLMs), tools, and control logic into explicit execution structures. However, constructing high-quality agentic workflows remains largely manual and requires substantial domain expertise. Recent studies have explored automatic agentic workflow generation from historical task-solving records, but they mainly produce LLM-centric workflows, where real tool executions are abstracted and simulated by LLM nodes, limiting the usability and stability of generated workflows. To address these limitations, we propose FlowScout, an execution-guided framework for generating tool-integrated agentic workflows from historical task-solving records. Specifically, FlowScout represents an agentic workflow as a directed graph composed of LLM nodes, tool-calling nodes, and dependency edges. It first mines a common tool coordination skeleton from historical records to construct an initial workflow, and then refines the workflow topology through Monte Carlo tree search guided by execution feedback. We evaluate FlowScout on four representative task domains and compare it with three baselines, i.e., PM4Py, ReAct and AFlow. Experimental results show that agentic workflows generated by FlowScout improve tool invocation correctness by at least 92.69% and execution quality by at least 17.66% over the baselines, while achieving lower performance variation across repeated runs.

AI 总结：本研究构建含300份简历的平衡语料库，用LLM流水线提取软技能并检验13项假设，发现候选人多以叙事披露软技能，资历影响领导力表述率，关键词筛选会遗漏软技能。

链接：https://arxiv.org/abs/2608.10046

机构：Technical University of Munich（慕尼黑工业大学）； Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）

作者：Aidin Azamnouri, Nouran Ayad, Justus Bogner, Stefan Wagner

英文摘要：Soft skills shape collaboration among ML engineers, data scientists, and software engineers building ML-enabled systems, yet what we know about them comes almost entirely from the demand side. Job advertisements, surveys, and hiring manager interviews capture what employers ask for. How candidates themselves articulate these competencies has not been studied, and existing CV-mining work is both keyword-based, so it cannot see skills conveyed through narrative, and descriptive, reporting frequency rankings without testing whether group differences exceed sampling variation. We close both gaps. Using a balanced corpus of 300 curated CVs spanning the three roles, we extract explicitly listed and implicitly narrated soft skills with an LLM-based pipeline validated against a human-annotated ground truth, a distinction that existing extractors were not designed to make. We then convert the demand-side literature's claims into 13 falsifiable hypotheses about role signatures, seniority progression, and disclosure style, and test them with effect sizes under family-wise error control, so that candidate-side data can corroborate or contradict the demand-side account rather than merely illustrate it. Eleven hypotheses are supported, one partially, and one refuted. Candidates disclose soft skills through narrative rather than keyword lists by roughly three to one, and most so for the competencies employers value most: leadership, coordination, and mentoring (88-96% narrative). Seniority nearly triples the odds of articulating leadership. That competency, assumed universal in prior work, is articulated by software engineers at half the rate of their peers. Technical candidates do articulate soft skills, but a keyword-based screening systematically misses them.

AI 总结：本文通过对212项研究的系统综述，提出PIML的四类分类方案，发现其在PHM中性能优于传统方法，但存在领域偏向问题，未来需关注可迁移设计等方向。

链接：https://arxiv.org/abs/2608.10047

机构：University of Stuttgart（斯图加特大学）； Fraunhofer Institute for Manufacturing Engineering and Automation IPA（弗劳恩霍夫制造工程与自动化研究所IPA）

作者：Christopher Braun, Julian Raible, Marco F. Huber

英文摘要：In modern industry, keeping complex systems reliable, safe, and efficient hinges on Prognostics and Health Management (PHM). Machine Learning (ML) has largely driven advancements in diagnostics and prognostics, yet purely data-driven models face inherent limitations, such as poor generalization, an inability to infer causal relationships, and a lack of interpretability. Physics-Informed Machine Learning (PIML) helps mitigate these limitations by incorporating prior physical knowledge directly into the ML pipeline, thereby fostering growing interest in its application to PHM. This work investigates how PIML is being leveraged in the context of PHM through a systematic literature review of 212 studies. The review introduces a four-class classification scheme, consisting of observational bias, inductive bias, learning bias, and hybrid approaches, and further categorizes studies by PHM task. Across all four classes, the reviewed studies consistently demonstrate improved predictive performance over conventional baselines across a broad range of assets, although the literature is heavily skewed toward lithium-ion batteries and bearings, and dominated by problem-specific solutions. Overall, the review indicates that physics-informed approaches already provide tangible benefits, whereas claims of improvements concerning some of the aforementioned limitations lack sufficient supporting evidence. Future research should prioritize transferable design patterns, benchmarks comparing integration strategies, and uncertainty-aware models that are lightweight and robust enough for online deployment in real-world settings.

AI 总结：该研究针对中小企业财务指导的观测策略排序问题，提出CAR-PL方法，通过85078个公司-月度数据验证，其在毛利润等指标上表现优异，可实现多动作会计日志下的财务指导类别排序。

链接：https://arxiv.org/abs/2608.10050

机构：Foresight-AI（预见人工智能）； Intuit（英图易公司）

作者：Shrutendra Harsola, Vignesh Subrahmaniam, Vikas Raturi, Kamalika Das, Xiang Gao, Kratika Gupta, Ruocheng Guo, Padmaja Jonnalagedda, Ananya Pramod, Sricharan Kumar

英文摘要： Small and medium-sized businesses need timely financial guidance, yet historical accounting logs record self-selected and often co-occurring business changes rather than randomized recommendations. We formulate this setting as observational policy ranking: from pre-decision financial information, a policy selects one of 34 ledger-derived business-change categories for a target financial KPI. Using 85,078 company-month observations from 7,505 firms, we introduce Covariate-Adjusted Residual Policy Learning (CAR-PL), an action-wise R-learner that operates directly on multi-hot logs and regularizes selection by observational support. We compare CAR-PL with an uplift T-Learner, a conservative contextual value model, a zero-shot LLM, and non-personalized references on company-disjoint held-out firms under a shared model-assisted scoring rule. CAR-PL has the highest Gross Profit point estimate (0.084), the T-Learner has the highest Revenue point estimate (0.085), and the contextual value model has the highest Quick Ratio point estimate (0.062). CAR-PL and the T-Learner are not statistically separated on either growth KPI in matched company-clustered comparisons, while CAR-PL selects 33-34 categories and produces less concentrated selections across the catalog. Outcome-model-only scoring retains the same KPI-level point-estimate leader or top pair, and category rankings remain similar when the all-zero treatment reference is replaced by the most common training co-action pattern. These findings support objective-specific ranking of SMB financial guidance from multi-action accounting logs.

AI 总结：本研究独立复现LeWorldModel在TwoRoom上的结果，发现评估协议（如目标偏移量）会显著影响性能，还揭示单步预测准确率无法预测长程规划成功、批量归一化层会夸大验证损失等关键结论。

链接：https://arxiv.org/abs/2608.10145

作者：Joyjeet Singh

英文摘要：LeWorldModel trains a latent world model with a prediction loss and a single anti-collapse regulariser, and reports approximately 87% of goals reached on TwoRoom, its simplest diagnostic environment. We reproduce that result by independent reimplementation on roughly $25 of rented compute, with all evaluation on one laptop CPU. We reach 94.0% at the repository's evaluation goal offset, against 84.0% for the authors' own released checkpoint measured under our protocol on identical episodes, and we reproduce the reported representation result directly (position probe Pearson r = 0.9988 against a reported 0.996). Reaching that point required four conventions that determine the outcome and appear in no released configuration file: dense action gathering across a frameskip block, a programmatically-set action-encoder width, ImageNet pixel normalisation, and action z-scoring. A reproducer following the released configurations alone obtains a model whose predictor cannot converge. The evaluation protocol is itself contested by the released material. The paper's appendix and the repository's configuration specify different goal offsets and step budgets; on the authors' own weights these yield 14.0% and 84.0%, and only the configuration's values reproduce the reported figure. On fifty identical episodes, changing nothing but how the goal is constructed moves that checkpoint from 84.0% to 8.0%. Two findings generalise. One-step prediction accuracy does not predict long-horizon planning success: across three checkpoints spanning a sevenfold range in prediction error, including the authors' own, it orders short-horizon success monotonically and fails to order long-horizon success at all. And a batch normalisation layer inflated our reported validation loss by up to a factor of 300, concealing a training loss that was flat throughout.

AI 总结：本研究提出机制可解释性的谱可识别性定理，利用Koopman算子构建模型内在指纹，在GPT-2 small等模型上验证了谱的收敛性及相关性质，为机制可解释性的基础组件提供了首个可识别性理论。

链接：https://arxiv.org/abs/2608.10172

机构：IISER Bhopal（印度博帕尔科学教育与研究所）； IBM Research（IBM研究院）

作者：Ashim Dhor, Pin-Yu Chen

英文摘要：Mechanistic interpretability explains models by identifying circuits inside them, but has no way to tell whether a circuit is a property of the model or an artifact of the method that found it. Sparse autoencoders illustrate the problem: different seeds and widths recover materially different features from the same activations, and no theory says whether that variability is incidental or structural. We put dictionary learning for interpretability on an identifiability footing. Treating the forward pass as a controlled dynamical system with depth as time and lifting it with the Koopman operator yields a finite linear realisation whose \emph{spectrum} is a coordinate-free property of the model. We prove the spectrum is recoverable from $M$ calibration samples at rate $M^{-1/2}$ up to permutation - to our knowledge the first identifiability theorem for a mechanistic-interpretability primitive, with a matching minimax lower bound, a median-of-means variant for heavy-tailed activations, and a dissociation theorem: whenever the realisation is non-normal, the directions carrying activation variance and the directions carrying information across depth cannot coincide. The identifiable object and the legible object are not the same object. On GPT-2 small, Gemma-2-2B and Qwen3-8B-Base the spectrum converges everywhere and attains the predicted exponent on Qwen3-8B-Base ($0.506 \pm 0.031$); shortfalls collapse onto one curve against each cell's sample threshold. Koopman modes beat random directions but lose to principal components on indirect-object identification, with the gap decaying $4.1\times$ in depth-distance, as the theorem predicts. The Koopman spectrum is an identifiable, model-intrinsic fingerprint with a stated error bar, not a legible decomposition.

AI 总结：本研究提出进化语言模型 ELMER，通过微调 Qwen3-8B 并结合 oDPO 优化，实现自然语言策略搜索与编译，提升进化搜索效率，证明语言可作为可执行程序空间的可引导搜索表示。

链接：https://arxiv.org/abs/2608.10196

机构：New York University（纽约大学）； University of Malta（马耳他大学）

作者：Matthew Siper, Ahmed Khalifa, Julian Togelius

英文摘要： Program evolution can measure whether a mutation helped, but it rarely controls how far the mutation moves in behavior space. Syntactic edit size is an unreliable proxy: a small code change can alter nearly every action, while a larger rewrite can preserve the same execution trace. We introduce an Evolutionary Language Model that searches over natural-language policy descriptions and compiles typed programs for execution. A fully fine-tuned Qwen3-8B model learns three task-conditioned operations: conditional semantic mutation, natural language to domain-specific language (GPTL) compilation, and GPTL to natural language translation. The model is fine-tuned with conditional input on the mutation strength (low, medium, high) using Direct Preference Optimization (oDPO). Across 252 fixed-budget evolutionary searches, oDPO improves both behavioral calibration and finite-budget search efficiency. Natural-language attains the highest observed held-out fitness. Our analysis shows that the condition input (mutation strength) systematically changes semantic edit composition and that language mutations preserve more parent fitness at matched small-to-moderate behavioral displacement. These results show that language can serve as a steerable, execution-grounded search representation over executable program space.

AI 总结：本研究通过匹配积分器协议，对比哈密顿神经网络（HNN）与参数匹配前馈基线，在单摆、开普勒二体问题上验证了HNN在降低能量、轨迹漂移及提升物理一致性上的优势。

链接：https://arxiv.org/abs/2608.10235

机构：African Institute for Mathematical Sciences (AIMS) Senegal（塞内加尔非洲数学科学研究所）

作者：Lenick Kemunto Nyabuto, Yae Ulrich Gaba, Birahim Tewe

英文摘要：Hamiltonian Neural Networks (HNNs) parameterize conservative dynamics through a learned scalar Hamiltonian, providing an architectural prior that is absent from generic vector-field neural networks. We evaluate this prior under a controlled protocol in which an HNN and a parameter-matched feedforward baseline are trained on the same RK4-generated trajectories, use the same central-difference derivative targets and optimization settings, and are integrated at inference with the same RK4 scheme. Results are reported over five independent training seeds. On the nonlinear pendulum, the HNN reduces mean energy drift by 42-fold and mean trajectory MSE by 15.8-fold at T = 100, approximately 16 pendulum periods. Its energy drift also remains bounded and exhibits substantially lower seed-to-seed variability than the standard-network baseline. An energy-stratified analysis shows that the difference becomes more pronounced as trajectories explore more nonlinear regions of phase space. As an additional diagnostic, we examine an explicit Störmer--Verlet-style rollout of the learned HNN. Because the learned Hamiltonian is not constrained to the separable form H(q,p) = T(p) + V(q), the standard symplecticity guarantee of velocity Verlet does not directly apply. We further apply the same matched-integrator protocol to the three-dimensional Kepler two-body problem. The HNN again exhibits lower trajectory, energy, and angular-momentum drift than the parameter-matched baseline. These experiments provide a controlled study of how Hamiltonian parameterization affects long-horizon prediction and physical consistency across two conservative dynamical systems.

AI 总结：该研究提出PLGA注意力机制，其在$G_{LM}=I$时精确包含SDPA，还证明了推理崩溃定理，在测试样本上的分块与顺序评分结果与TruthfulQA度量偏差极小，相关证明核心已通过Lean 4机器验证。

链接：https://arxiv.org/abs/2608.10288

机构：Fromthesky Research Labs LLC（弗洛姆斯基研究实验室有限责任公司）

作者：Burc Gokden

英文摘要：The Large Language Model from Power Law Decoder Representations (PLDR-LLM) and its attention, Power Law Graph Attention (PLGA), replace the fixed bilinear form of scaled dot-product attention (SDPA) with a learned, input-generated bilinear operator $G_{LM}$, built from a positive tensor $A_{LM}$ by elementwise power laws. The architecture is fully specified, verified against pinned reference releases; claims are labeled theorem, conditional theorem, measurement, or conjecture. Unconditionally: PLGA contains SDPA exactly at $G_{LM}=I$; $A_{LM}$ and $A_P$ are strictly entrywise positive, with Perron-Frobenius structure on $A_{LM}$; the DAG regularizer has the NOTEARS walk-counting form and positivity obstructs exact acyclicity; and, under nonresonance (satisfied by standard rotary frequencies), a commutant criterion identifies which operators preserve relative-position dependence. An inference-collapse theorem: exact input invariance of deductive outputs collapses inference to generalized SDPA with a constant operator. Measured invariance: relative fluctuations of $10^{-6}$ and below; perturbation bounds quantify but do not certify cached inference; the assembled proxy misses the decoding margin. A conditional three-stage mechanism (rotary twirl, concentration, row-map contraction) is measured on a released checkpoint. Blockwise training and scoring under the global Gram are stated with explicit target exposure; on tested samples, block and sequential scoring select identical answers and agree on the published TruthfulQA probability-mass metric within $5\times 10^{-5}$ per item. Self-organized criticality enters as a phenomenological framework with an intrinsic order parameter; open claims become falsifiable conjectures. Selected proof cores are machine-checked in Lean 4.

AI 总结：本研究以哈里斯县轻罪保释听证会为对象，通过训练机器学习模型分析法官决策，发现法官整体呈算法式行为但存在差异，识别算法无法解释的决策可完善司法系统。

链接：https://arxiv.org/abs/2608.10400

作者：Riya Manchanda, Eric Chen, Chloe Zhu, Cynthia Rudin, Brandon Garrett, Songman Kang

英文摘要： What if judges already behave like algorithms? As artificial intelligence and algorithms are deployed in many settings, including the judicial system, many have debated whether judges should be allowed to rely on them. Instead, we ask whether judges follow predictable, algorithmic-like rules already. If judges already follow consistent, formula-like rules based on discrete and static factors such as criminal history, age, and charge type, then judicial behavior may be improved. However, if judges rely on individualized information that cannot be identified through court data, then standards-based decision-making may be more challenging to understand or improve. This work explores these questions by studying judicial decision-making in misdemeanor bail hearings in Harris County, Texas. Using available court data, we investigate whether magistrate judges follow what resembles an algorithm; whether they consider the same variables in their decision-making; and whether they are consistent with themselves and with each other. To do this, we train machine learning models for each judge, measure variable importance metrics to determine important variables for each judge's decision-making, and analyze outcomes of similar cases for judges. Our results reveal that these judges generally behave algorithmically: their decisions can be captured by small, interpretable formulas. However, in some cases, judges differ substantially, leading to surprising inconsistency and unequal treatment across similar defendants. Identifying cases where algorithms do not explain judicial decision-making can improve the justice system by focusing attention on decisions where individualized standards, rather than rules, better explains outcomes.

AI 总结：该研究针对时间序列模型，分析了延迟可恢复性、报告与功能使用的问题，发现多数模型存在延迟报告正确但实际未使用对应历史的情况，提出的路由方法可实现预测与报告的对齐。

链接：https://arxiv.org/abs/2608.10433

机构：Supcon Technology（中控技术）； College of Artificial Intelligence, Zhejiang University（浙江大学人工智能学院）

作者：Qipeng Qian, Yuntao Qian

英文摘要：Forecast accuracy does not tell us which past inputs produced a prediction. We separate three questions for time-series models with known delay structure: can the true delay be recovered from the observed data, does the model report it, and does the forecast actually use the same history? We first derive input-conditioned recoverability measures that separate intrinsic ambiguity from model error. We then prove that a delay report can become arbitrarily reliable while forecast risk approaches the oracle even though the predictor still uses the wrong lag. This failure also appears in finite samples on the point-delay task: among forecasts with a correct delay report and normalized excess risk within 10\% of the oracle, the reported history is functionally unused under our matched masking test in 55.4\% of N-HiTS cases and 92.7\% of TCN cases. Finally, we show that routing the prediction through the reported history removes off-report bypass paths; a hard one-hot control achieves exact fixed-report alignment. The main conclusion is simple: a good forecast, even with a correct delay report, does not show that the model used the right history.

AI 总结：该研究指出检测信号平均效应与学习基于该效应行动存在差异，提出奖励信噪比下限，引入SHE模型，在三个推荐数据集上发现学习获取策略失效，因数据集SNR低于下限。

链接：https://arxiv.org/abs/2608.10441

作者：Ying Yuan

英文摘要：Many pipelines can pay a per-example cost to acquire an auxiliary, model-derived observation -- an LLM's structured reasoning, a slow oracle, an expensive measurement -- and then must decide when the acquired signal is worth using. Our thesis is a distinction that is easy to miss: detecting that such a signal helps on average is not the same as learning to act on it per instance, and a reward-SNR floor governs when the second is even possible. Even when the signal is faithful and an in-sample oracle picking the top-b examples by realized reward shows a sizable apparent gain, no deployable policy can learn when to acquire it: across per-impression, cluster, regime, and uplift-tree granularities, learned routing never beats random, and a matched-moment noise placebo reproduces >=100% of the oracle's apparent gain -- the apparent "learnable structure" is order statistics of noise. We explain this with one distinction, detecting a mean effect vs. learning a per-instance acquisition policy, and a reward-SNR detectability floor: routing is estimable offline only if the reward SNR rho clears rho*(N) ~= 2.8/sqrt(N), with a positive control confirming a true low-SNR limit rather than a broken pipeline. As a concrete instantiation we introduce Structured Hypothesis Embeddings (SHE): a frozen LLM turns a user history into ranked, confidence-scored, evidence-grounded intent hypotheses, fused into a recommender. On three public datasets (MIND, REES46, Amazon-Beauty), SHE is faithful and calibratable, yet its value is backbone- and regime-conditional (significant over an ordered GRU, +0.0114, 95% CI [+0.0030, +0.0209], but a global redundancy gap indistinguishable from zero), and learned acquisition collapses at every granularity because all three datasets sit below the floor. The realizable unit is a design-time regime gate, not a per-instance policy. We release code and a one-command reproduction.

AI 总结：该研究提出成本感知跨层迁移方法，解耦LLM角色，在低成本层级完成大部分搜索，跨层部署提示词，在多任务多模型上实现成本大幅降低且性能不劣于同层级优化。

链接：https://arxiv.org/abs/2608.10694

机构：IBM Research（IBM研究院）

作者：Tal Oved, Roi Pony, Oshri Naparstek, Udi barzelay

英文摘要：Evolutionary optimization of LLM prompts and agentic programs (e.g., GEPA) is dominated by fitness evaluation: scoring each candidate runs an answering LLM over a validation set, so the evaluator's price tier dictates total search cost. We restructure that search by decoupling the three roles an LLM plays, running the high-volume answering role on the cheapest tier, reserving a strong model for the rare reflection/variation operator, then exploiting upward cross-tier transfer to deploy the cheaply evolved prompt on a stronger target. We contribute a cost-controlled characterization of when cheap-tier search substitutes for target-tier search, and where it fails. Across four tasks (HotpotQA, IFBench, LiveBench-Math, HoVer) and eleven models in four model families, the resulting prompt matches or exceeds same-tier optimization while placing over 96% of search tokens on the cheapest tier, at 5.6-14x lower search cost, rising to 25-54x where reasoning tiers emit long chains of thought on every fitness call.

AI 总结： 本研究提出情境化行为数据框架，构建3200个对比性行为场景，发现LLMs有稳定且模型特异性的行为特征，提出行为模式轴控制LLM行为，表明其类人格倾向是可测量可控的行为模式。

链接：https://arxiv.org/abs/2608.10703

作者：Haoze Liu, Run Liu, Haiying Xu, Jiahui Han, Siyuan Fang, Siyu Yan, Huiqi Deng, Guanchu Wang, Na Zou

英文摘要：Large language models (LLMs) increasingly act in interactive settings where their behavioral styles affect user experience, safety, and downstream decision making. Existing LLM personality studies largely rely on self-report questionnaires administered in first-person settings, making the resulting profiles sensitive to surface elicitation choices and poorly grounded in concrete model behavior. In this work, we introduce a situated behavioral-data (B-data) framework for studying and controlling LLM behavioral personality. We construct 3,200 contrastive behavioral scenarios spanning 20 behavioral patterns and four prompt registers, grounded in validated psychometric facets such as BFI-2, DOSPERT, and HEXACO. Using this framework, we find that LLMs exhibit stable and model-specific behavioral profiles, while also revealing register-dependent shifts across first-person decisions, advice-giving, and task execution. We then show that these behavioral patterns can be controlled through Behavioral Mode Axes (BMAs), activation-space directions derived from contrastive behavioral traces. Compared with response-derived BMAs, which are more prone to trait drift, thought-derived BMAs more faithfully capture the intended behavioral mechanism and provide cleaner control over situated behavioral styles. Our results suggest that LLM personality-like tendencies are better understood not as abstract self-report traits, but as measurable and controllable behavioral modes grounded in concrete interaction contexts. Our code and data are available at this https URL.

AI 总结：该研究针对SA-NODEs长时间轨迹近似的误差双指数恶化问题，提出模型预测与弗洛凯两种状态重置策略，经四个基准实验验证了误差规律。

链接：https://arxiv.org/abs/2608.10738

机构：Friedrich-Alexander-Universität Erlangen-Nürnberg（弗里德里希-亚历山大-埃尔兰根-纽伦堡大学）； School of Pedagogical & Technological Education (ASPETE)（教育与技术教育学院（ASPETE））

作者：Ziqian Li, Nikolaos M. Matzakos

英文摘要：We study the approximation of dynamical systems by semi-autonomous neural ordinary differential equations (SA-NODEs) over long time horizons. For a single network trained on the whole horizon, the available error bound deteriorates double exponentially in the horizon length. We develop two training strategies that avoid this barrier, each built on a reset of the state. The model predictive strategy partitions the horizon adaptively and restarts every window from observed data: when training meets a prescribed tolerance on every window, the composite model meets it uniformly in time, with a parameter budget linear in the horizon for targets with a bounded, uniformly regular reachable tube. The Floquet strategy addresses autonomous targets with a stable limit cycle and uses no data at deployment: a certified contraction of the learned return map confines the error to linear growth in the number of elapsed periods. For the time-periodic architecture we deploy, the scalar certificate degenerates; we prove instead a uniform-in-time orbital guarantee whose hypotheses are measured on the trained model, and an obstruction showing that, for an exactly periodic learned field, small one-period error and a contracting stroboscopic map cannot hold at once. Numerical experiments on four benchmarks confirm the predicted error laws and measure the hypotheses of every guarantee.

AI 总结：该研究针对线性二次随机最优控制中基于策略方法的高成本与不稳定性问题，提出路径积分值匹配算法，结合时间差分学习、吉尔萨诺夫定理与经验回放，在低维场景效率提升一个数量级，高维场景缓解模式坍塌，为复杂SOC问题提供可扩展解决方案。

链接：https://arxiv.org/abs/2608.10777

机构：Westlake University（西湖大学）； School of Engineering（工程学院）

作者：Bangyan Liao, Chenglei Yu, Yuchen Yang, Chuanrui Wang, Zhisheng Song, Peidong Liu, Tailin Wu

英文摘要：Linear Quadratic Stochastic Optimal Control (LQ-SOC) establishes a fundamental framework for steering noisy dynamical systems and has recently gained renewed interest in the machine learning community. However, current state-of-the-art policy-based methods suffer from prohibitive computational costs and instability due to their heavy reliance on full-trajectory simulation. To overcome these limitations, we propose a paradigm shift toward a value-based approach by revisiting Path Integral Control (PIC). Although standard PIC suffers from the same high-variance bottleneck as policy-based methods, we discover that by truncating and marginalizing the original path integral formulation, we can derive a temporal recursive form of the value function. Building upon this theoretical foundation, we propose the Path Integral Value Matching (PI-VM) algorithm. Specifically, we employ temporal-difference learning to approximate the recursive value dynamics, and further integrate the Girsanov theorem with experience replay to enable off-policy training. We benchmark PI-VM against SOTA policy-based methods across various SOC benchmarks and sampling tasks. Empirical results demonstrate that PI-VM matches SOTA precision with an order-of-magnitude efficiency gain in low-dimensional settings, while effectively mitigating mode collapse in high-dimensional scenarios. Consequently, PI-VM offers a scalable solution for solving complex SOC problems.

AI 总结：针对表格基础模型推理成本高、蒸馏后损失上下文适应性的问题，提出TACTICL框架，剪枝Transformer层并替换为轻量适配器，在47个基准数据集上可替换85%层且性能无显著下降，对数据偏移鲁棒。

链接：https://arxiv.org/abs/2608.10837

机构： TU Dortmund University（多特蒙德工业大学）； Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习与人工智能研究所）

作者：Mykhailo Koshil, Matthias Feurer, Katharina Eggensperger

英文摘要：The strong performance of foundation models for tabular tasks comes at substantial inference costs. Distilling models into task-specific architectures reduces model size and computational demands but also sacrifices in-context adaptability. Here we introduce TACTICL, an automated task-aware compression framework for tabular in-context learning models that jointly prunes transformer layers and replaces them with lightweight adapters trained on downstream tasks, thus blending in-context with in-weight learning. We study TACTICL on 47 benchmark datasets and show that we can substitute up to 85% of layers without substantial performance drop on a given downstream task. We further show that TACTICL maintains robustness to data shifts, leaving its in-context ability intact. Overall, TACTICL provides a robust framework for exploiting the depth-wise redundancy of tabular foundation models by combining task-specific adaptation and structured compression. We provide the code at: this https URL

AI 总结：ReOrder-OPD 提出以代理指标估计提示级教师延续可靠性并排序提示，结合 vanilla OPD 训练，在 Qwen3、Gemma4 等多模型数学及代码任务中提升了在线策略蒸馏效果。

链接：https://arxiv.org/abs/2608.10905

作者：Ximo Zhu, Ruiqi Liu, Rong Wang, Ping Wu, Xiang Zheng, Wenzhuo Xu, Xubin Yao, Zhiyuan Yan, Bo Li, Jun Gao, Xiaolei Lv

英文摘要：On-policy distillation (OPD) applies token-level teacher supervision to student-generated trajectories, but this supervision is not always reliable. Existing methods use local confidence or teacher-student agreement to weight, filter, or truncate the sampled trajectory. These signals do not directly determine whether the teacher can continue a student prefix to a correct answer, and trajectory-level interventions can conflate one rollout's unreliability with low expected training value of its prompt. We define prompt-level teacher continuation reliability $R$ as the teacher's probability of reaching a correct answer from a student prefix, averaged over prefixes and trajectories induced by the current student. Oracle experiments show that high-$R$ prompts yield larger OPD gains and that descending-$R$ training outperforms random and ascending orders on a fixed prompt pool. Because estimating $R$ requires many teacher continuations, we use the maximum ROUGE-5 F1 between one independent student rollout and verifier-correct same-prompt teacher trajectories. Across ten equal-frequency bins of this actual score, mean $R$ rises monotonically, showing that the proxy separates coarse reliability levels. ReOrder-OPD sorts prompts by the proxy, then draws independent on-policy training trajectories for vanilla OPD. It improves every matched aggregate comparison across Qwen3 and Gemma4 mathematics settings and Qwen3 code settings. Gains in all six FiRe-OPD and ExOPD settings show that prompt ordering complements within-trajectory supervision.

AI 总结：该研究以稀疏自编码器（SAE）隐集合重叠度为相似度度量，发现SAE特征不通过简单特征袋语义组合，其激活集合与人类概念判断存在显著不匹配。

链接：https://arxiv.org/abs/2608.11197

机构：Heidelberg University（海德堡大学）

作者：Nikolai Bolik, Lennart Stöpler, Artur Andrzejak

英文摘要：Shani et al. (2026) show that LLM representations broadly recover human category boundaries, while failing to reflect fine-grained typicality structure. Their analysis uses cosine similarity over dense model representations. We revisit their approach using overlap over active sparse autoencoder (SAE) latent sets as a more interpretable similarity measure. We first verify that this set-level measure is meaningful: SAE latent sets can recover union-like compositional structure in controlled toy models and induce semantically coherent neighborhoods in natural text. Extending the human-concepts analysis to SAE set similarities, we find that SAE activation sets do not recover human category boundaries or within-category typicality more faithfully than dense embeddings or residual-stream states, but instead track model-internal similarity structure. To probe this gap further, we study active latent sets under well-controlled semantic modifications, revealing a substantial mismatch between human judgements of conceptual change and change in the SAE active set. We interpret this as evidence that, outside idealised settings, SAE features do not compose via simple bag-of-features semantics.