跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 23:55 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 00:36 — 2026-11-09 00:36（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-08 23:55最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 3,292 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 23:54（北京时间）
版本更新 · v2arXiv:2610.41970

When Does Test-Time Search Help World Action Models? An Empirical Audit of Candidate Selection and Simulator Integrity

Jun Liu, Dajie Sun, Zhenglun Kong, Zhenjiang Fan, Peiyan Dong, Fan Yang, Wenbin Zhang, Geng Yuan 等 11 位作者

原文摘要

World-action models increasingly apply test-time scaling, spending extra inference computation on candidate selection and adaptive allocation to improve control. Such gains are credible only when candidates carry exploitable signal, nominal compute savings become real speedup, and evaluation stays reliable. We audit all three on Cosmos Policy and RoboCasa with a premise-first, pre-registered methodology. On clean data, a learned value selector is 1.66 pp worse than random; a hindsight oracle gains only 1.40 pp, with an episode-level interval spanning zero; and 82% of states show identical candidate outcomes, leaving little selection headroom. Token pruning cuts per-forward FLOPs by up to 47% but yields at most a measured 1.15$\times$ end-to-end speedup on the deployed path (1.25$\times$ on a decode-excluded path), short of a 1.5$\times$ target, and our adaptive-allocation experiment is inconclusive under a power gate. We further identify and fix a silent rendering corruption whose rate rises sharply along compute-heavy planning paths while leaving the official direct-policy result unaffected, and release a detector, fix, and scripts. These findings show why test-time scaling should be audited as a chain of premises (decision signal, realized efficiency, evaluationintegrity) rather than by success rate alone. Conclusions are scoped to the tested configuration.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04887

FourSight: Stable FP4 RL Post-Training via Sequence Filtering and Sparse Channel Compensation

Yining Wei, Tianyuan Wu, Gu Gong, Yuechen Tao, Yinghao Yu, Xiaowen Chu, Wei Wang

原文摘要

Reinforcement learning (RL) post-training increasingly targets low-bit deployment, with NVFP4 weight-and activation quantization (W4A4) becoming the state-of-the-practice format. However, integrating NVFP4 into RL degrades rollout quality and amplifies cross-engine training-inference mismatch (TIM), destabilizing training. We show that these failures are concentrated rather than uniform - severely mismatched tail tokens concentrate in a few outlier sequences, while policy weights remain largely intact and quantization error concentrates in a few high-variance activation channels. Guided by this, we present FourSight, an algorithm-system co-design with two targeted solutions: TIM-aware sequence filtering that excludes drifted trajectories from policy updates, and sparse precision compensation that keeps only top-variance channels in BF16 while retaining native NVFP4 elsewhere. We further design a fused SpliceGEMM kernel with specialized prefill and decode datapaths to minimize overhead. FourSight sustains near-BF16 accuracy and strong FP4 deployment quality across models and engines, while improving step-to-accuracy by 1.76-2.60x and staying within 2.3% of FP4 step time up to 120B-scale models.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04886

Modelling lock-in of AI adoption through skill erosion

Renaud Lambiotte

原文摘要

Generative AI can improve immediate performance but may erode the human skills required for future work. We study a model in which individuals tend to imitate successful peers, while their independent skills grow with practice and erode with reliance on AI. Because each agent's skill reflects their history, non-users and AI users develop different skill distributions, which we derive exactly. Skill erosion can produce bistability and hysteresis between a low-adoption, high-skill state and a high-adoption, low-skill state. When agents rarely change behaviour at random, the two transitions are asymmetric. A single AI user spreads through a population of experts only if AI-assisted work earns more than expert work, whatever the timescale of skill adaptation. A single non-user, by contrast, can lead an AI-dependent population back to independent work only if they regain enough skill before returning to AI, which becomes easier the more persistent behaviours are. As AI improves, adoption can jump abruptly, and a sufficiently long increase in its benefit, such as a period of low prices, can leave a population relying on AI after the benefit has returned to its initial value. Skill erosion thus creates a history-dependent switching cost that can make widespread AI adoption difficult to reverse.

cs.AI · physics.soc-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.17613

MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification

Hehai Lin, Zixuan Wang, Ming Yan, Peidong Wang, Shilei Cao, Minzhi Li, Bosheng Ding, Juepeng Zheng 等 9 位作者

原文摘要

Large language model (LLM)-based multi-agent systems (MAS) can solve complex problems beyond the reach of a single agent by decomposing tasks and coordinating complementary capabilities. Despite extensive research on MAS, existing work largely focuses on specific aspects or individual phases of their development and operation, resulting in fragmented perspectives with objectives and signals that are difficult to reconcile across these different settings. To bridge these disconnected perspectives, we conceptualize MAS development and operation as a three-phase lifecycle spanning design-time orchestration before execution, runtime intervention during execution, and post-hoc attribution after execution, and introduce MAS-Gate, a unified node-centric quantification applicable across these phases. Modeling each execution as a directed acyclic graph, MAS-Gate combines within-node utility, which estimates a node's contribution through changes in reference-answer likelihood, with inter-node strength, which approximates semantic uptake and potential downstream reach. We adapt this shared quantification to three objectives: providing a structure-aware dense reward for Orchestrator training, training an Editor to act on execution prefixes using paired rewards from completed edited and unedited trajectories, and supplying risk-ranked nodes as auxiliary evidence for LLM-based post-hoc attribution. Experiments spanning interaction environments, knowledge-intensive multi-hop question answering, general reasoning, and post-hoc attribution demonstrate that MAS-Gate improves workflow construction, targeted runtime editing, and LLM-assisted error localization over corresponding phase-specific baselines. Together, these results establish MAS-Gate as a unified structural interface for improving MAS generation, dynamic editing, and error attribution throughout the lifecycle.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.38946

MAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems

Hehai Lin, Qi Yang, Chengwei Qin

原文摘要

Training-time multi-agent system (MAS) design seeks to learn reusable orchestration policies, yet prevailing approaches remain largely one-shot: an Orchestrator generates a system but only observes and learns from its terminal outcome. This paradigm discards execution trajectories that expose system-level failures and contain fine-grained information beyond the terminal outcome, leaving no direct basis for revising the source MAS, evaluating the updated MAS, or learning from the resulting contrast. To this end, we introduce MAS-Loop, an execution-grounded framework that closes this feedback loop by coupling an Orchestrator with a trajectory-conditioned Refiner. For each task, the Orchestrator constructs and executes a source MAS to obtain an outcome score and an intermediate trajectory. Conditioned on the trajectory, the Refiner localizes an actionable failure, formulates a trajectory-grounded diagnosis, and proposes a bounded patch to the agents, information flow, or execution configuration. The executable updated MAS is re-executed on the same task to measure its realized outcome under stochastic execution. This pair-MAS comparison provides complementary learning signals: the Orchestrator learns to generate strong systems with fewer recoverable failures, whereas the Refiner learns to expose and repair observed weaknesses, thereby driving policy-level co-evolution across training iterations. Experiments show that MAS-Loop achieves the strongest overall performance among the evaluated baselines, with consistent gains from refinement across all evaluated benchmarks. The co-evolution process also yields MAS-JudgeCorpus, a dataset of execution-grounded source-updated pairs with orchestration- and trajectory-level supervision, which can provide the community with support for MAS reward modeling and trajectory-aware investigation.

cs.MA · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.08218

How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs

Mark Kozdoba, Shie Mannor

原文摘要

Compositional priors describe the generic properties of layered functions in deep Bayesian models, where deep neural networks with random weights are a canonical example. In the wide-network limit, the prior is a Gaussian process (GP) with a depth-dependent kernel, and its behaviour as depth grows has been extensively studied through this kernel. Here, we study another case, where each layer itself is a vector valued Gaussian process, and our aim is similarly to understand the limiting behaviour of the prior as depth grows. Previous GP work has established that for the radial basis function (RBF) kernel and a certain range of bandwidths $r$, the prior degenerates in the limit, converging to the set of constant functions, which is not useful as a probabilistic model. In this paper we establish several new results. First, we identify a sharp bandwidth threshold $r_c(d) = Θ(\sqrt{d})$ above which the limit is degenerate, strengthening the earlier bounds. Second, and more importantly, we show that for $r$ below the threshold $r_c(d)$ the prior converges to a limit distribution $π_{\bar{Z}}$. We also prove that these distributions are non-degenerate and non-Gaussian, with non-vanishing dependence between coordinates. In contrast to the previously known degenerate regime, deep Gaussian process priors can therefore admit non-trivial limits. Empirically, we verify the threshold across a range of dimensions $d$, and demonstrate a complex multimodal behaviour of the limit distributions $π_{\bar{Z}}$, a regime that becomes increasingly narrow with $d$ and would be hard to identify without knowing the threshold.

cs.LG · cs.AI · math.ST · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04867

One Assistant, Many Memories: Benchmarking Real-World Group Assistance When Recall Is Not Enough

Zhanghao Hu, Linhai Zhang, Qian Zhao, Qi Zhu, Yuan Hua, Di Liang, Jiasheng Si, Xin Zhao 等 11 位作者

原文摘要

The value of memory lies not only in recall but in using it to provide appropriate assistance. Recent benchmarks test memory use in personalisation and agentic tasks, but seldom evaluate assistance without fixed answers or integration across multiple participants. Group chats make both challenges more acute: an assistant must integrate information from multiple members, track revisions and conflicts over time, and produce one response for the group. Yet existing group memory benchmarks rely on synthetic conversations and inherit constrained evaluation from general memory benchmarks, focusing on recall against fixed answers or decisions over a closed set. We introduce GroupAssistBench, the first memory benchmark from real-world group conversations with a deployed group assistant, covering 80,299 messages in 50 groups and costing over $53K. Over the same histories, GroupAssistBench evaluates memory recall (L1) with reference answers and memory use (L2) with service requests without fixed answers across single, distributed, and conflicting memories (M1--M3). Requests are verified to require group history, memories are anchored to their sources, and L2 uses tailored rubrics with penalties derived from real user feedback. Across evaluations of frontier models with full context, retrieval methods, and memory systems, the strongest memory system rivals full context on recall but falls far behind on use, especially for distributed and conflicting memories. Together, two additions that relate retrieved memories and bind remembered facts as response constraints bring consistent gains, showing that group memory systems must improve use, not recall alone.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.03301

An Axiomatic Framework for Reinforcement Learning in Open Multi-Agent Systems

Jianhong Wang, Yang Li, Samuel Kaski, Jonathan Lawry

原文摘要

Open multi-agent systems, where only a subset of agents are controllable, are central to real-world domains such as smart grids, yet lack a principled foundation for reinforcement learning algorithm design. We study this setting through n-agent ad hoc teamwork (NAHT), a recent framework for learning in open multi-agent environments. We propose an axiomatic framework that derives value function learning from the Shapley axioms (Efficiency, Symmetry and Linearity), treating them as structural constraints rather than heuristic design choices. This formulation builds on a novel NAHT decomposition, which characterises the fundamental difference between open and fully controllable multi-agent systems, and establishes a cooperative game-theoretic foundation for learning. We further show that enforcing these axioms on learning individual value functions recovers the Shapley value for Dec-POMDPs, providing a principled bridge between reinforcement learning and classical cooperative game theory. Building on this framework, we introduce Shapley Machines and Banzhaf Machines, two generic algorithmic templates that can be instantiated with standard reinforcement learning methods. When applied to strong base algorithms such as IPPO and POAM, our methods consistently improve learning efficiency and generalisation to unseen agent types and conventions across NAHT benchmark tasks. The code of experiments is published on https://github.com/hsvgbkhgbv/axiomatic-rl-naht.

cs.LG · cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04848

Amortized Nonlinear Variable Selection with Prior-Data Fitted Networks

Jin Zhu, Junxian Zhu

原文摘要

Variable selection is an important task for interpreting potentially complex systems in fields such as biology, business, and sociology. The importance of variable selection has attracted considerable attention in statistics and machine learning. In this paper, we are mainly interested in model-agnostic variable selection for identifying variables that have general nonlinear dependence on the response. We propose MambaPFN, short for Model-Agnostic Markov BlAnket selection with Prior-data Fitted Networks, which is built upon the Transformer, a building block of many popular large language models. Specifically, we consider a functional-mapping perspective on variable-selection learning, in which the Transformer is treated as a learnable mapping from a dataset to its relevant variables. To learn this mapping, MambaPFN introduces three new components: (i) a faithful, rich, and scalable scheme for generating pretraining data, (ii) an objective that targets each variable's posterior inclusion probability, and (iii) a modified Transformer architecture tailored to variable selection. Once pretrained, MambaPFN is applied to new datasets without parameter updates. Empirically, MambaPFN achieves desirable variable-selection performance in simulation studies and exhibits a scaling law---more pretraining datasets and larger models can continuously improve its performance. Applied to a Facebook comments dataset, MambaPFN selects the fewest variables and achieves the highest computational efficiency and predictive performance, improving upon the best baselines by about 20%.

cs.AI · stat.ME · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.20267

CleanVideo: Adaptive Concept Erasure for Text-to-Video Diffusion Models

Junchi Liao, Hongji Li, Wenrui Zhou, Lijie Hu

原文摘要

Concept erasure aims to selectively eliminate undesired visual semantics from pre-trained generative models without compromising their general utility. Extending concept erasure from images to video is nontrivial. Target concepts emerge gradually and vary across frames and denoising steps. As a result, fixed interventions may miss the target or introduce blurring, jitter, and content distortion. We propose CleanVideo, a selective erasure framework that performs low-dimensional subspace intervention controlled by a tri-modal gating mechanism. By jointly processing spatiotemporal visual features, timestep signals, and textual semantics, CleanVideo determines where, when, and whether to intervene, steering erased content toward natural surrogate concepts when such surrogates can be clearly defined while preserving non-target content. Experiments on three video diffusion models show that CleanVideo effectively erases target concepts while maintaining visual fidelity and temporal coherence, outperforming existing baselines under frame-level and video-level evaluations and under concept-recovery attacks when the protected pipeline remains intact.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.20827

Auditing Provenance Sensitivity in LLM Agent Action Selection

Junchi Liao, Qiang Huang, Rui Qian, Xutao Mao, Juntao Cheng, Kangning Cui, Yu Li, Jingyu Sun 等 9 位作者

原文摘要

LLM agents choose tools and arguments from context that mixes user requests, tool outputs, retrieved records, memory, and untrusted text. Evidence can be relevant without being authorized to determine a decision, so a correct action need not be grounded only in permitted evidence. We introduce a target-specific authorization audit that labels context factors separately for each tool and argument target. Its primary test holds the task, proposition, position, and policy fixed while changing only the proposition's source authority. We then test behavior when valid evidence is weakened and use context-subset interactions as a secondary localization diagnostic. Across 450 controlled next-action tasks and multiple open-weight LLM families, trusted and untrusted variants produce different actions in 5.4 percent of competing cases versus 1.7 percent of supporting cases. Under controlled degradation, unauthorized competition is retained in a full-correct, mixed-error, clean-correct pattern in 2.4 percent of comparisons, with a 95 percent confidence interval from 2.1 to 3.0 percent. These are controlled stress-set rates, not deployment prevalence. The models respond to textual source-authority cues, but this does not prevent untrusted evidence from influencing their actions.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04841

DGC-Net: Cross-Modal Dynamic Routing with Global-Guided Compensation in Multimodal Sentiment Analysis

Linan Zhu, Huaijing Wu, Xiao Han, Yuhao Wang

原文摘要

User-generated videos, including opinion vlogs and video reviews, provide a rich source of people's attitudes toward products, services, and social topics. Understanding the sentiment expressed by speakers is important for analyzing online opinions, as transcripts alone may not capture the attitude and intensity conveyed through vocal tone and facial expressions. Multimodal sentiment analysis (MSA) addresses this need by integrating textual, acoustic, and visual cues. However, these cues are often subtle, noisy, and inconsistent across modalities. Existing local affective cue modeling methods typically operate within individual modalities and overlook global contexts from other modalities. This may cause cross-modal affective cue inconsistency. Hierarchical global-local fusion methods integrate global semantics with fine-grained local affective cues. However, they commonly determine the relative contributions of the two representations implicitly, preventing the global-local contributions from adapting to the sample-dependent reliability of local cues and resulting in either insufficient use of informative local cues or excessive interference from unreliable ones. To address these issues, we propose DGC-Net, a Dynamic Gating and Global-Guided Compensation Network for MSA. DGC-Net mitigates cross-modal affective cue inconsistency through cross-modal contribution-aware dynamic expert routing. This mechanism uses auxiliary global contexts to guide local expert selection. Moreover, global-guided dynamic compensation fusion alleviates sample-dependent global-local contribution imbalance while preserving global semantic as the primary anchor and adaptively incorporating expert-refined local cues. Experiments on five multimodal benchmark datasets demonstrate the effectiveness and general applicability of DGC-Net, and ablation studies verify the contribution of each proposed component.

cs.AI · cs.MM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04838

Found by Search, Broken by a Shortcut: Transfer and Tampering of Searched Intrinsic Rewards

Chase J. Metoyer

原文摘要

Can a search over innate drives find intrinsic rewards that help a reinforcement-learning agent learn, transfer to a task it never saw, and resist an exploit that was absent during the search? Each candidate reward combines four generic events (a new view, a pickup, a drop and a toggle), each with a weight, a relief and a refill rate. We ran three pre-registered stages; the search protocol was locked in a public, timestamped commit before any search result existed. CMA-ES and an equal-budget random search used 1,560 PPO training runs, and the final evaluation and tamper test used 340. On the held-out task, KeyCorridorS3R2, the CMA-ES-selected reward (E) beat task-only PPO, episodic novelty and the random-search-selected reward (R) in all 3 registered comparisons, all of them meaningful by the registered size rule. Among these generic rewards E transferred best; the earlier paper's satiation reward, which on this task is given hand-wired key and locked-door events, did better (20 of 20 seeds solved against 4 of 20; descriptive). On UnlockPickup, where that reward uses generic events, E's mean area exceeded it by 0.276 (descriptive). On the training tasks there was no registered difference between E and R: both E-over-R tests missed. A free reset action, absent during the search, collapsed E's learning on DoorKey-8x8 (mean area 0.829 without it, 0.136 with it; registered) to below task-only PPO (descriptive). The searched drives helped on every task tested, but a reward given task-specific events did better on the held-out task, and selection gave E no protection against an exploit absent from the search.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04836

HTCE: Homeomorphism-inspired Topological Cross-Scene Experience Canonicalization and Reuse for Object Navigation

Xiaoran Xu, Yupeng Wu, Tianyu Xue, Xuanran Dong, Yifan Xu, Xiaoshan Yang, Changsheng Xu

原文摘要

As embodied agents perform object-goal navigation across residential environments, they accumulate successful experiences whose semantic structure recurs across scenes even when geometric trajectories do not. Reusing such experience is challenging because differences in region naming and observation granularity produce distinct graph representations of similar approaches, while meaningful differences in anchors, branches, and endpoints must stay distinguishable. We introduce HTCE, a homeomorphism-inspired topological framework that canonicalizes and reuses navigation experience. Feature and topology subdivisions characterize representational variations, and their semantically constrained reductions produce comparable semantic sequences and structural signatures while preserving semantic anchors, branching relations, and navigation endpoints. HTCE then retrieves historical successful approaches through subdivision-aware matching as guidance for a frozen vision-language policy. Canonicalization compresses the experience index losslessly, merging 17.7--23.6\% of distinct stored route descriptions while retaining full task performance. Under a single frozen vision-language backbone shared by all compared systems, HTCE attains the best SR and SPL in every setting---59.9\%/31.8\% on HM3D v0.1, 71.0\%/31.5\% on HM3D v0.2, and 46.6\%/16.6\% on MP3D---with SR gains of up to 4.9 points and structured retrieval contributing up to 2.8 SPL points. The code is available in https://github.com/startracker0/htce.git

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04834

Feeling of Knowing in Large Language Models

Zichuan Fu, Xian Wu, Jingtong Gao, Wenlin Zhang, Jiaxuan Li, Binhao Wang, Yimin Deng, Guojing Li 等 12 位作者

原文摘要

Post-training updates change what large language models (LLMs) can answer, but may leave their answerability judgments misaligned. We study this knowledge-judgment desynchronization through functional feeling of knowing (FoK), which supports selective generation, retrieval triggering, and model routing without implying subjective experience. We propose two trainable channels: a knowledge channel that changes answerability and a FoK channel that judges the current knowledge state. Three stages train them: on-policy supervised fine-tuning (OP-SFT) updates knowledge from corrected on-policy answers; knowledge-delta FoK training (K$Δ$-FT) adapts judgments across intermediate knowledge states; and FoK-guided policy optimization (FGPO) trains the subsequent answer or explanation. Factual-QA experiments, cross-dataset evaluation, and three sequential updates show that explicit FoK alignment improves judgment quality on updated knowledge. MMLU and ARC-Easy separately assess capability preservation.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2508.21380

The Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural Network

Elias Sandmann, Sebastian Lapuschkin, Wojciech Samek

原文摘要

Recent mechanistic work has uncovered learned algorithms within neural networks, from modular arithmetic to search and planning in game-playing agents. But does algorithmic structure guarantee algorithmic behavior? We investigate this in Leela Chess Zero, the strongest neural chess engine, where prior work identified learned look-ahead. By extending the logit lens to its move-selecting policy network, we discover that correct puzzle solutions--including immediate checkmates--often appear in intermediate layers but are systematically overridden in the final output, a phenomenon we term "forgotten puzzles". Replicating prior analyses on these positions, we find that look-ahead operates normally--future moves of the correct continuation are represented, causally important, and linearly decodable--ruling out a failure of the algorithm. Instead, late layers increasingly shift toward safe play over aggression. To test whether this shift drives the override, we steer the model against these preferences and recover 71.7% of forgotten puzzles, providing causal evidence that safety priors override algorithmically computed solutions. These findings show that algorithmic structure does not guarantee algorithmic behavior: a model can internally solve a problem and still output the wrong answer.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04825

UniFlow: Unified Multi-Scale Flow Matching for Time Series Generation

Shibo Feng, Wei Li, Min Wu, Chunyan Miao, Peilin Zhao

原文摘要

Real-world time series exhibit complex dynamics across multiple temporal resolutions, yet effectively incorporating multi-scale information into generative modeling remains challenging without increasing generative complexity. We propose UniFlow, a unified framework that integrates multi-scale representation learning with efficient non-autoregressive generation through a shared-semantic discrete interface. Specifically, a multi-scale tokenizer employs shared-index voting to consolidate complementary temporal information into a single public-ID sequence, while scale-specific codebooks preserve the information required for reconstruction. Building on this unified representation, we develop geometry-aware categorical flow matching, which initializes transport from learned low-rank anchors and generates public identities non-autoregressively. This design captures multi-scale temporal structure without requiring multiple generative token streams or sequential token decoding. Experiments across four benchmarks and both short- and long-term settings demonstrate improved generative fidelity, strong cross-scale consistency, and substantial inference speedups over representative autoregressive and diffusion-based baselines. Code is available at https://github.com/William-Liwei/uniflow

stat.ML · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.18805

RecoAtlas: A Benchmark and RL Environment for LLM Recommendation Agents Optimizing Set-Level Utility

Imad Aouali, Flavian Vasile, Clijo Jose, Otmane Sakhi, Alexandre Gilotte, Benjamin Heymann

原文摘要

LLM recommender agents increasingly produce structured reports: sets of items accompanied by natural-language justifications. Yet existing benchmarks often focus on reranking small candidate sets or judging reports primarily by semantic plausibility, providing limited support for evaluating and training agents based on set-level utility. We introduce Recommender Atlas (Agentic Tasks for Learning and Assessment in Shopping), or RecoAtlas, a benchmark and reinforcement learning environment grounded in user behavior. RecoAtlas provides a shopping toolkit for product retrieval, complementarity, and diversity. Given a shopping query, an agent uses these tools to generate a structured recommendation report. Behavioral reference sets support exact-recovery evaluation and the training of a learned bundle-level reward that supplies feedback for policy optimization with RL. Its controlled tool environment exposes agents to semantic and behavior-aligned tools, enabling systematic analysis of how LLM reasoning, tool signals, and tool-use policies contribute to performance. Across controlled experiments, performance scales with model capacity and test-time compute, and improves with stronger tools, while semantic plausibility does not necessarily translate into behavior-grounded utility. RecoAtlas provides a foundation for training and evaluating shopping assistants to move beyond semantic plausibility toward coherent, behaviorally grounded recommendation sets.

cs.IR · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04819

Reconstructing Fraudulent Strategies in Online Payments via Interpretable Inverse Reinforcement Learning

Huilin He, Weiyu Han, Linbo Shao, Ruobing Zuo, Xiao Tan, Shuai Chen, Dawei Cheng

原文摘要

Payment fraud causes financial losses and undermines users' trust in web payment services. Although fraud detection is a critical defense for payment security, complex and diverse fraudulent behaviors can still evade detection. Generating fraud samples for data augmentation can broaden detectors' coverage of different fraud patterns. However, existing methods matching the distribution of transaction attributes alone do not ensure that generated sequences preserve the sequential relationships among transaction choices, payment feedback, and subsequent behavioral adjustments. To this end, we propose PaySeqGen, an interpretable inverse reinforcement learning framework that reconstructs fraud behavior policies from fraudsters' observed payment trajectories. We design a mechanism for constructing candidate actions to support plausible payment sequence generation while enabling exploration. The framework also learns interpretable behavioral rewards that capture fraudsters' preferences across different transaction contexts. By alternating between reward learning and policy optimization, the framework reconstructs policies that generate new fraud sequences for detector augmentation and learns interpretable rewards supporting sequential fraud-pattern analysis in real trajectories. Experiments in real-world payment scenarios at Ant International, a leading global digital payment provider, show that PaySeqGen outperforms state-of-the-art generative augmentation methods. Reward-based trajectory analysis also identifies fraud patterns of practical value, helping analyst locating suspicious segments and examine multistep fraud tactics. Evaluation in the deployed system of online payment further confirms its effectiveness.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.31275

Personalized to Persuade: The Effects of Contextualization and Warmth on Trust and Reliance in Conversational AI

Mert Yazan, Suzan Verberne, Frederik Bungaran Ishak Situmeang

原文摘要

Contextualization is a form of personalization in which the message is framed in a context meaningful to the recipient, using their interests and background. Personalization is a known persuasive strategy of artificial intelligence (AI) systems in politics and marketing. However, the persuasive effect of contextualization in everyday tasks, where users often lack prior knowledge, remains unclear. We ran a $2\times2$ between-subjects experiment ($N = 407$) in a fictional scenario where participants had no prior opinions or knowledge. We examined how contextualization, combined with conversational warmth, shapes the persuasive power of an AI assistant arguing against expert recommendations and users' reliance on it. Our findings show that the neutral, non-contextualized assistant was the most persuasive. Contextualization and warmth each reduced persuasiveness on their own, but their interaction increased it. Reliance was present in all conditions, and neither cue changed it detectably. Trust predicted persuasion and reliance, yet neither contextualization nor warmth had an indirect effect through trust. Participants with higher self-reported AI literacy relied more on the assistant without trusting it more. Our study extends AI personalization research from political opinions to everyday decisions made without prior knowledge. The results suggest that users are more likely to be persuaded by, and defer to, an AI assistant than an expert, even without personalization. AI persuasion experiments should therefore include untailored assistants and measure decisions; the cues that changed persuasion did not detectably change reliance.

cs.HC · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04817

The Pen is Mightier than the Pixel: Natural Textual Unlearnable Example for Large Vision Language Models

Chenyu Yi, Jiawen Zong, Sami Hormi, Bingquan Shen, Xudong Jiang, Alex Chichung Kot

原文摘要

The proliferation of Large Vision Language Models (LVLMs), trained on vast and often sensitive datasets, raised concerns regarding data privacy and unauthorized usage. Unlearnable Examples (UEs), which subtly perturb training data to mislead the models, have emerged as a promising defense method. This paper presents the first exploration of UEs specifically on LVLMs, which poses unique challenges due to their inherent multimodal nature. We propose a novel text-based perturbation method, Natural Textual Unlearnable Examples (NTUE), which can effectively mislead LVLMs by subtly manipulating the image label, establishing a shortcut between an identity of interest and a separate target, without introducing factual misinformation or affecting readability. Comprehensive experiments compared with traditional UE methods demonstrate the superior performance of NTUE. Our findings show that NTUE achieves a high success rate with a poison rate as low as 5%, underscoring its potential as a practical and robust solution for protecting multimodal data in the era of LVLMs.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.22377

Forecasting Brain Tracer Distribution from Pre-Contrast MRI: A Comparison of Direct Regression and Flow Matching

Qinghui Liu, Jon André Ottesen, Thu Nguyen, Geir Ringstad, Ingrid Mossige, Siri Fløgstad Svensson, Sissel Riis Kalstad, Atle Bjørnerud 等 10 位作者

原文摘要

The brain fluid clearance system can be studied with intrathecal contrast-enhanced magnetic resonance imaging (MRI). By injecting a tracer into the spinal canal and performing MRI over 24--48\,h, one can measure how a tracer injected into the cerebrospinal fluid spreads through the brain. As this is an invasive procedure requiring several MRI scans, we ask how much of the later tracer distribution can be predicted from the pre-contrast scan and elapsed time alone. Using 104 training patients (878 MRI volumes), we compared a direct image-to-image regression model with a more complex generative model based on conditional flow matching, and tested both on 23 held-out patients and on 51 patients from a separate cohort with idiopathic normal pressure hydrocephalus (iNPH). Relative to simply copying the pre-contrast scan, the direct model reduced the mean absolute error (intensities normalized to $[0,1]$) from 0.089 to 0.036, about 60\%, in held-out patients and from 0.075 to 0.056, about 25\%, in the iNPH cohort. The reduction held in every sampled elapsed-time interval and brain compartment, and errors remained largest at 20--30\,h and in the ventricles, where enhancement is strongest. Its predicted change maps agreed with the observed tracer enhancement rather than only reproducing anatomy. The generative model was less accurate in both cohorts. A substantial part of the later tracer distribution is therefore predictable from the patient's brain anatomy as seen on pre-contrast MRI, and the added model complexity gave no benefit at this data scale. Whether this accuracy suffices for a given clinical use remains to be established; with prospective validation, such forecasts could help simplify the MRI protocol used to assess brain clearance.

eess.IV · cs.AI · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04814

Think Less, Locally: Local Preference Learning for Reasoning Compression

Muyao Yuan, Liyan Xu, Weizhan Zhang, Muyan Jiao, Jiangnan Li, Jinchao Zhang, Jie Zhou

原文摘要

Large reasoning models achieve strong performance on challenging tasks, but their long chain-of-thought often incurs substantial inference costs by continuing to deliberate after sufficient information has been obtained. Existing reasoning compression methods primarily operate on reasoning trajectories, paying less attention to the local decision of whether further reasoning is necessary given the current state. We propose LoCo, a local preference learning method for reasoning compression. LoCo detects candidate overthinking states from the model's own traces, freezes the corresponding reasoning prefixes, regenerates shorter verified continuations from the same states, and trains on the resulting state-conditioned preference pairs with DPO. This formulation teaches the model when to continue reasoning and when to conclude, rather than simply encouraging shorter trajectories overall. We construct training data entirely from self-generated mathematical traces and evaluate LoCo on five mathematical and three code generation benchmarks. LoCo reduces completion length by 41.7\%--45.4\% on mathematics and 23.4\%--36.3\% on code, while maintaining or improving accuracy and achieving the best AUC across all code benchmarks. LoCo consistently improves the accuracy-efficiency trade-off on mathematics and transfers effectively to code generation despite math-only training, demonstrating the cross-domain generality of local preference learning for reasoning compression. The code and model will be publicly released at https://github.com/MuyaoYuan/LoCo.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04809

RAHC: Rule-Augmented Hyper-Relational Knowledge Graph Completion for Materials Synthesis

Jiawei Sun, Sijia Xu, Zihan Chen, Zhengyi Yang

原文摘要

Scientific discovery depends on reusing experimental knowledge, yet records scattered across papers and repositories are often incomplete. In materials synthesis, recovering missing conditions requires reasoning about the target material and the observed context of a specific experiment. Hyper-relational knowledge graphs (HKGs) represent this context through qualifiers, but existing completion methods leave domain knowledge and experimental regularities implicit. We propose RAHC, a rule-augmented HKG framework for single-slot and joint multi-slot synthesis-condition completion. RAHC builds a traceable rule catalog from training records and retrieved literature, retrieves rules for each query-candidate pair, and separately encodes graph structure and rule evidence. Hard rules constrain candidate validity, while soft rules guide ranking. RAHC-G aggregates rules using global reliability; RAHC-Q additionally learns query-specific relevance. Gated fusion combines structural and rule representations, while tuple-conclusion rules provide cross-condition evidence for joint completion. Experiments on five materials-synthesis datasets show improvements in single-slot and joint completion under Semi-inductive and Open-Answer Inductive settings, with Semi-inductive MRR gains of up to 15.6% over MAYPL. RAHC also improves performance on the entity-disjoint ILPC'22 Small benchmark, supporting transfer to fully inductive KG completion. These results support experimental condition selection, synthesis planning, and the reuse of scientific knowledge.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04807

Asymptotic Optimality of $cμ$-Rule for LLM Inference Scheduling under Memory Constraint

Zhenghao Li, Shengbo Wang, Nian Si

原文摘要

Large language model (LLM) inference, the process by which a pre-trained model receives an input prompt and generates output tokens sequentially, has become increasingly important with the widespread deployment of LLM-based applications. As inference workloads continue to scale, GPU memory has emerged as a critical bottleneck: the long input prompts and generation sequences common in agentic and reasoning workloads lead to substantial key-value (KV) cache usage. In this paper, we study the resulting online scheduling problem from a queueing perspective. Requests arrive stochastically with heterogeneous prompt and output lengths, undergo prefill and autoregressive decode, and compete for a finite KV-cache capacity. Unlike classical queueing models, the duration of a processing step depends on both prefill computation and KV-cache I/O, so service capacity is jointly determined by computation, memory access, and memory occupancy. We develop a fluid model that reduces the system to a multiclass single-server queue with effective service rates capturing computation, memory access, and memory capacity. This fluid analysis yields a $cμ$ priority rule, where the effective service rate $μ$ is jointly determined by computational speed, memory bandwidth, and memory capacity. We prove that this rule minimizes cumulative holding cost in the fluid model and, for a finite workload, also minimizes completion time and maximizes full-run output-token throughput. We then construct a feasible scheduling policy for the original finite system and prove that its scaled dynamics converge to the optimal fluid policy. Finally, experiments on a real LLM serving engine using an NVIDIA H800 show that practical implementations of the proposed priority rule substantially reduce average latency while maintaining high throughput relative to existing scheduling policies.

math.OC · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04805

Where Is the Truth When AI Agents Disagree? Dependence-Aware Belief Propagation for Unsupervised Truth Discovery (Extended Version)

Laure Berti-Equille

原文摘要

LLM agents often give conflicting answers to the same question, and many deployed agents are variants of one base model, so their errors are correlated. We study truth discovery among such agents: inferring the true answer and each agent's reliability without labels. Classical truth-discovery and crowdsourcing estimators reward an agreeing bloc and can fall below majority vote. We propose BP-TD, which adds per-agent decorrelation weights to mean-field variational inference on a one-coin Dawid-Skene model, so that agents sharing a base model count together as about one vote. Its first iteration is exactly a weighted vote; later iterations estimate agent reliability. With 13 local agents on MMLU, BP-TD beats majority vote without any labels (0.716 vs. 0.624 on 160 questions; 0.707 vs. 0.674 on 10,000) and ranks agents by their true accuracy, which classical estimators invert. The gain depends on the pool: over 2,852 sub-pools of four benchmarks, decorrelation helps when the largest correlated bloc is weaker than the other agents and hurts when it is the strongest, and we found no label-free statistic that tells the two cases apart. Labels change the picture quickly: with 20 labelled questions, selecting the single best agent is more accurate than every aggregator we tested on MMLU, ARC and TruthfulQA.

cs.AI · cs.CL · cs.DB · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.42147

Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention

Ales Kubicek, Andrea Caciolai, Liangzu Peng, Sukrit Sumant, Benjamin Hoover, Fraser Greenlee, Ruairidh M. Battleday, Radim Urban 等 10 位作者

原文摘要

Agentic workflows are increasingly shifting towards long-horizon tasks, such as open-ended scientific work, where models benefit from long context windows. However, at ultra-long context (above 1M tokens), full attention is prohibitively expensive. A promising approach is sparse attention, in which a dedicated indexer selects a subset of keys for the attention. Yet current methods of indexing either still have quadratic cost in context size or lose accuracy at ultra-long context scale. We address this with Latent Sparse Attention (LSA), an efficient attention method that maintains accuracy at ultra-long context. In LSA, keys are hierarchically clustered in a learned latent space, and queries score the hierarchy of clusters instead of scoring every key, making prefill, decode and training faster at long context. We propose two variants, Distilled-LSA (D-LSA), which can be applied to pre-trained models via distillation, and Native-LSA (N-LSA), which is trained natively on the next-token loss alone. On GLM-5.3-FLASH (QWEN-3.8-27B) at 10M tokens, D-LSA speeds up one attention layer by 22.7x (72.4x) in prefill and 4.6x (42.5x) in decode over its original sparse attention (full attention), while keeping similar accuracy across a variety of tasks. N-LSA matches the accuracy of full attention with a training speedup of 1.6x per layer at 128k tokens. LSA offers practical and efficient attention for models to benefit from ultra-long context.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.31585

DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers

Shun Kenney, Teppei Suzuki

原文摘要

The remarkable scalability of Transformers has expanded their application to 3D computer vision, where camera-aware positional encoding is crucial for providing spatial cues in multi-view geometry. Recent advancements have established the practice of using camera parameters---such as extrinsics or projection matrices---as relative positional encoding into the query, key, and value vectors of the attention mechanism. However, when scaling up the training recipe of novel view synthesis (NVS) models with the camera-based positional encoding, we observe a significant issue: model performance stagnates in the late stages of training. In this paper, we investigate the cause of the performance bottleneck when scaling up and demonstrate that storing rotation and translation given by the positional encoding in the same dimensions of the value vector causes indeterminacy in their independent identification, hindering training scalability. To address this, we propose Decoupled Pose Positional Encoding (DPPE), a novel camera-based positional encoding that explicitly decouples rotation and translation. Extensive evaluations on NVS tasks demonstrate that DPPE enables stable long-term training even in scaled-up training setup. Furthermore, it exhibits superior generalization performance in extrapolation settings, such as handling an increased number of viewpoints and zoom-in scenarios. Code is available at https://github.com/sbintuitions/dppe.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04792

Density-Aware Reward Scaling: A Reinforcement Learning Framework for Reward-Proportional Sampling

Ria Shekhawat, Abhijeet Sinha, Yingtao Zhu, Dianbo Liu

原文摘要

Reinforcement learning objectives that maximize expected return can concentrate probability mass on a small subset of high-reward outcomes, limiting diversity when multiple distinct solutions are desirable. We introduce Density-Aware Reward Scaling (DARS), a simple reward-processing mechanism that promotes reward-proportional sampling in continuous outcome spaces while retaining standard policy-gradient training. DARS estimates the local density of outcomes within each on-policy rollout group and inversely scales rewards by this density. The method requires no learned density model, auxiliary objective, critic, or modification to the underlying policy-gradient objective. In a controlled multimodal navigation task, DARS-GRPO avoids the single-mode collapse exhibited by GRPO and closely recovers the target mode allocation. Applied to text-to-image prompt adaptation, DARS-GRPO consistently improves image and prompt diversity across datasets, Policy LMs, and reward settings while maintaining good semantic alignment. These results show that density-aware reward scaling provides a lightweight way to improve coverage of diverse high-reward outcomes within existing reinforcement-learning pipelines.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04787

ReSI-Math: Exploring Recoverable Capability Frontiers for Efficient Reasoning Improvement

Yao Cui, Zhen Yang, Yuandong Wang, Yangfu Zhu, Tianyu Wo, Zhenzhou Shao

原文摘要

Reinforcement learning with verifiable rewards (RLVR) has become an effective approach for improving mathematical reasoning in large language models. However, a fundamental question remains: when a model fails to solve a problem, does it truly lack the underlying capability? In this work, we reveal that direct failure does not necessarily imply inability. Some reasoning failures can be recovered by exploring the model's own trajectories, exposing a recoverable capability frontier: a policy-dependent region where solutions are not reliably generated through direct decoding but can be elicited through trajectory-level search. Based on this observation, we introduce ReSI-Math, a framework that explores recoverable capability frontiers and converts recovered capabilities into data-efficient RLVR supervision. ReSI-Math uses Self-Judge-guided evolutionary search to identify recoverable failures under a fixed policy and adaptively selects frontier problems for sequential RLVR as the policy evolves. On Qwen3-VL-8B, correct-incorrect trajectory crossover produces 272 verifier-confirmed correct offspring from 621 attempts (43.8%). After three sequential one-shot RLVR stages, the MATH500 and WE-MATH average improves from 78.71 to 80.16. Under matched single-problem RLVR, random selection reaches only 53.31 versus 54.16 for frontier-guided Q1.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗