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
+0已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 07:12 · 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 08:17 — 2026-11-09 08:17（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：2026-11-09 07:12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 2026-11-09 07:10（北京时间）
新论文 · v1arXiv:2610.38577

Episodic looking - using reinforcement learning to bias perception enhances few-shot and continual learning with protection from forgetting

David Rawlinson, Gideon Kowadlo

原文摘要

There is a fundamental contradiction between the desire for models that can generalize, and models that can continuously adapt to recent input with changing statistics. These conditions, captured in few-shot and continual learning settings, can bias or disrupt learned representations. This harms generalization to a broader context, leaving the model unable to overcome input variance. This paper proposes a solution based on the Complementary Learning System architecture (CLS), in which a Short-Term Memory (STM) delegates generalization to a slow, statistical Long-Term Memory (LTM). Delegation is achieved by working in a space of robust, generalized perceptions produced by the LTM. With this separation, the STM can focus on memorizing recent input and avoiding interference between memories. We show that on an image classification task, the resulting CLS model is more resistant to forgetting in a domain-incremental continual learning setting than a baseline ResNet LTM, and generalizes more effectively in a few-shot setting than other continual learners. In the continual setting, overall accuracy is slightly worse than existing continual learning models, but with a different mix of performance characteristics. Results analysis suggests that the model is limited by the representations and representational plasticity of the LTM. In future work, we will seek to address this by replaying STM memories to the LTM.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38573

CALM: Conflict-Aware Lifecycle Memory Governance for Long-Horizon Language Agents

Chang Li, Xianhao Ou, Xinyan Ma, Hao Li, Haoyuan Xu, Jiafeng Liang, Xiaohan Wang, Jiajun Chai 等 10 位作者

原文摘要

A memory can be outdated for present-day reasoning yet indispensable for reconstructing the past. Relevance-based retrieval overlooks this tension: semantic relevance, evidence-grounded validity, and query-specific eligibility are distinct. We propose CALM, a conflict-aware lifecycle memory governance framework that decouples persistent memory preservation from query-time admission. CALM converts heterogeneous records into evidence-grounded memory cells, updates validity and lifecycle states using support, conflict, and dependency signals, and admits query-appropriate evidence through training-free or learned gating informed by temporal applicability. Across LongMemEval-S and LoCoMo with Qwen and GPT backbones, CALM outperforms state-of-the-art baselines, achieving the best overall accuracy. Compared with simple filtering and reranking, query-conditioned admission further improves evidence selection. Conflict-blocking and robustness analyses show CALM suppresses erroneous retrieved memories while retaining useful evidence. Historical-reconstruction experiments demonstrate that preserving superseded records supports accurate earlier-state reasoning without compromising current-state answers.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38570

Do Audio LLMs HEAR Pain? Tracing Acoustic Evidence from Speech to Language Reasoning

Wenqi Li, Xiangjue Dong, Sulaiman Vesal

原文摘要

Large audio language models (LALMs) can process speech directly, but it remains unclear how well they use the non-lexical acoustic information that speech carries. We study this question through pain, using TAME-Pain, which contains pain-neutral Harvard sentences and spoken pain ratings recorded at different self-reported pain levels. We introduce HEAR, a four-stage diagnostic framework that traces pain-related information from the speech signal to the model's prediction, and apply it to seven closed-source and open-weight LALMs. On the Harvard sentences, where pain can only be inferred from the voice, all models perform at chance level, and same-speaker references or few-shot examples improve balanced accuracy by no more than six points. On the spoken ratings, the same models reach 87.5-99.7% balanced accuracy. Layer-wise probing of open-weight LALMs shows that pain can be decoded from early audio representations (74.1% balanced accuracy for binary prediction and 45.0% for three-class severity), but that this information, along with most pain-associated acoustic cues, decreases in deeper layers. In an acoustic perception test, weaker models cannot distinguish even large changes in these cues, whereas stronger models can but still fail to infer pain. Finally, we recover pain-related acoustic cues and directly reinject them as structured text into the prompt, which improves pairwise pain prediction by up to 32 points. These results indicate that current LALMs encode paralinguistic information in early layers that is largely unavailable when the model produces its answer.

cs.CL · cs.AI · cs.SD

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38568HF 社区推荐

A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement

Yu Liu, Youxing Li, Yuedong Tan, Zhiwei Yang, Zihan Su, Hanqi Feng, Shaojie Zhang, Libin Liao 等 20 位作者

原文摘要

Recursive self-improvement requires models not only to acquire useful training experience, but also to decide when their current experience has ceased to be useful. Existing methods often focus on what experience to generate next, while paying less attention to when fresh experience should be introduced. Many also construct training targets through self-consistency or majority voting, making supervision depend on the model's own uncertain predictions. We address these two questions separately: training dynamics determine when to acquire new experience, while the answers to new tasks remain independently checkable. A-RSI monitors reward variation and accuracy in training logs to refresh a task pool when its learning signal declines, without consulting validation or test scores. A static library of model-authored programs produces multimodal questions and derives their reference answers; we specify the task-generation contract, automatically verify chosen properties of the reward and refresh rules, and separately audit the generated answers. The training loop uses no external training examples or human-written answer labels. On the primary eleven-benchmark suite, A-RSI raises the performance average from 57.77 to 61.05 with 800 fresh tasks.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36991

SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented Generation

Zafer Sahinoglu, Abdulazeez Mohammed, Buse Yaren Kazangirler, Cahit Berkay Kazangirler

原文摘要

Retrieval-augmented generation (RAG) systems ground large language models (LLMs) by retrieving external evidence and conditioning generation on the retrieved context. Although dense retrieval is effective for local semantic matching, independently ranked retrieval can return redundant passages, miss cross-chunk dependencies, and provide incomplete evidence for multi-hop reasoning. We propose SpectRAG, a spectral graph-augmented retrieval framework that combines hybrid candidate seeding, weighted chunk graph construction, graph-based expansion, spectral relevance propagation, and token-budgeted context selection. Document chunks are represented by dense semantic embeddings and graph-spectral coordinates derived from a weighted chunk graph whose edges encode semantic similarity, document adjacency, section hierarchy, shared entities, citation links, and similarity between LLM-generated utility questions. At query time, SpectRAG builds a high-recall seed set using exact inner-product search and hybrid relevance signals, expands it over the chunk graph, re-scores candidates using graph proximity and spectral information, and assembles the final context under a fixed token budget. The goal is not merely to retrieve individually similar chunks, but to construct a context that is relevant, diverse, structurally connected, and sufficient for grounded reasoning. Experiments on MultiHopRAG, UltraDomain, and long-document question-answering settings show that SpectRAG improves broad evidence recovery and achieves competitive generation quality against dense, hybrid, HyDE, LightRAG, and NaiveRAG baselines. The results further indicate that graph-spectral structure is particularly useful for inference-oriented and cross-document retrieval, while highlighting trade-offs in early precision, computational cost, and domain-dependent performance.

cs.AI · cs.CL · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38566

Co-Evolving Policy and Rubric via Capability Awareness for Open-Ended Generation

Chengsheng Zhang, Wenshen Xu, Yuchuan Wu, Zhiyuan Yu, Junfeng Fang, Tianlong Wang, Bingxue Qiu, Yongbin Li 等 9 位作者

原文摘要

Rubric-based reinforcement learning (RL) offers interpretable, fine-grained supervision for aligning large language models (LLMs) on open-ended generation tasks. However, static rubric criteria may become saturated or remain beyond the policy's exploration, rendering the reward signals insufficiently discriminative. While recent efforts seek to guide sampling exploration or evolve rubrics, they fail to explicitly factor in how rubric difficulty should track the evolving policy's capabilities, resulting in a persistent mismatch between the optimization objective and the policy's current capability frontier. In this paper, we propose \textbf{Co}-Evolving Policy and Rubric via \textbf{C}apability \textbf{A}wareness (\textbf{CoCA}), a closed-loop framework that jointly adapts the rubric and policy through criterion-level diagnosis. Specifically, CoCA contrasts query-only and rubric-guided rollouts to characterize each criterion relative to the current policy, recalibrates criteria with mismatched difficulty, and identifies guidance-revealed capability gaps for frontier-based learning. Based on this insight, CoCA either expands rubric-conditioned frontiers through guided optimization or transfers qualified gains through on-policy self-distillation. As the policy updates, CoCA improves the capability diagnosis and enables more reliable distillation, thereby completing the co-evolution loop. Extensive experiments across diverse benchmarks and LLMs demonstrate that CoCA consistently improves performance over rubric-based RL methods. Moreover, CoCA promotes the internalization of guidance-revealed capabilities into query-only behavior while mitigating capability degradation.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38561

Persona Learning from Feedback for Personalized AI Assistants

Yiran Shen, Yu Xia, Liuyi Yao, Prithviraj Ammanabrolu

原文摘要

Personalizing AI assistants requires adapting their behavior to users' preferences and task contexts. Existing work elicits assistant personas through persona prompting or finetuning on persona-conditioned generations. However, persona descriptions alone do not identify what to change or preserve in a particular response, or which behaviors suit the current request. We introduce $\textit{Persona Learning from Feedback (PLF)}$, a framework that learns reusable, preference-grounded assistant personas as independent LoRA adapters on a shared frozen backbone. During training, a frozen self-teacher conditions on persona specifications and response-specific feedback to provide token-level supervision on each adapter's own generated prefixes. A feedback gate focuses corrective updates on responses judged to need improvement. At deployment, a supervised router uses the request or dialogue to select a single adapter or a fixed composition, without user-specific finetuning. We evaluate PLF on single-turn personalization with model-generated critiques and multi-turn tutoring with simulated students' reactions. Across both settings, PLF improves model-judged preference fit over fixed-persona policies and strong baselines including persona prompting and persona distillation, demonstrating how feedback-trained behaviors can be reused for adaptive assistant personalization without degrading general capabilities.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38551

PT$^3$: Prototype-Guided Self-Supervised Pretraining for Generalizable mmWave Human Point Cloud Representation

Ziyang Liu, Kieren Yu, Xiao Yang, Xin Yang, Kaishun Wu

原文摘要

Multi-source millimeter-wave (mmWave) observations offer an opportunity to learn human representations reusable across sensing tasks. However, sparse detections and multipath effects make these observations unstable, challenging existing point cloud pretraining methods. We propose PT$^3$, a prototype-guided self-supervised pretraining framework for mmWave human point clouds. PT$^3$ represents local states in spatial regions as sparse compositions of shared prototypes and learns their temporal evolution through autoregressive prediction. Observation consistency further stabilizes representations under radar perturbations. After pretraining on unlabeled sequences from multiple sources, the same frozen encoder supports action classification, dense point generation, joint pose estimation, and future motion prediction on datasets not used for pretraining. Across these tasks, PT$^3$ outperforms the compared pretraining baselines and achieves competitive or superior performance to task-specific models.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.14222

Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents

Afshan Hashmi

原文摘要

Retrieval-Augmented Generation (RAG) has become the standard paradigm for grounding Large Language Model outputs in external knowledge. Lumer et al. presented the first systematic evaluation comparing vector-based agentic RAG against hierarchical node-based reasoning systems for financial document QA across 1,200 SEC filings, finding vector-based systems achieved a 68% win rate. Concurrently, the PageIndex framework reported 98.7% accuracy on FinanceBench through purely reasoning-based retrieval. This paper extends their work by: (i) implementing and evaluating three retrieval configurations: Vector RAG, Tree Reasoning, and the proposed Adaptive Hybrid Retrieval (AHR), on a small controlled corpus of financial, legal, and medical documents; (ii) introducing a four-tier query complexity benchmark; and (iii) employing LLM-as-judge evaluation with GPT-4o-mini. Experiments reveal that Tree Reasoning achieves the highest overall score (0.900), but no single paradigm dominates across all tiers: AHR scores highest on cross-reference queries (0.850), all three methods tie on multi-section queries (0.929), and Vector RAG scores highest on the single multi-document query (0.900). Vector RAG has the lowest mean latency (1.61 s against 3.40 s for Tree Reasoning). On the first 50 publicly released FinanceBench questions, using the evidence snippets supplied with the benchmark as the retrieval corpus, Tree Reasoning scores 0.938, Hybrid AHR 0.901, and Vector RAG 0.821. Because the configurations also differ in document access, generation prompts and output length limits, these differences cannot be attributed to retrieval architecture alone. In these preliminary results the adaptive router does not outperform fixed tree reasoning overall (0.845 vs. 0.900); they motivate a larger evaluation of when query-based routing helps, rather than establishing its benefit.

cs.IR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38544

An Alignment Benchmark for Enterprise Agents on Era by Eon

Hai Sadon, Benjamin Gruenbaum, Doron Porat, Assaf Natanzon, Roy Zavida, Chen Dinachi, Or Itzahary

原文摘要

AI agents are widely used in enterprises to access business systems and act on them in pursuit of a goal. However, fulfilling a user's request can cause harm. Era by Eon is a product that creates a digital twin of a company by simulating its business systems and data. Its simulators implement the programming interfaces of real products. Our benchmark uses ten of these systems, including Salesforce, Zendesk, Jira and Slack. We tested whether agents would carry out harmful business requests or trust misleading information in company records. We ran 19 models on 41 tasks three times, for 2,337 runs. Of the 2,304 runs that produced an answer, 918 (40%) contained a violation. The most common were false claims about actions or records (290 runs), following planted instructions (266) and disclosing sensitive data to the wrong audience (249). Every attempted change was recorded and blocked before it took effect. Misleading Slack messages caused 16 models to report an incorrect ticket status in 47 of 57 runs. No model was free of violations. The four best models violated in 22 to 24% of their runs. Yet one of them, Nova Pro, did the task correctly in only 30 runs.

cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38532

From Leniency to Suspicion: How an Open Post-Training Recipe Changes Whom LLM Fact-Checkers Believe

Nouar AlDahoul, Yasir Zaki

原文摘要

LLMs increasingly fact-check online content with the poster's identity in view. However, it remains unclear which post-training changes how much a model's truth judgement depends on the poster's social class, and how such a change happens inside the model. This paper investigates job-based doubt, i.e., judging a claim false more often when the poster has a lower-status job, using fact-checked claims with randomised poster profiles in base and post-trained checkpoints of six model families. Our results reveal that: 1) post-training creates such doubt only with the open Tülu-3 recipe (OLMo-2 32B, Tülu-3 70B), not with Meta's, Alibaba's or Mistral's; the effect is under one percentage point but statistically reliable, exceeding training drift and replicating on independent claim sets; 2) in OLMo-2 32B, the model does not start noticing the poster's job more, but starts interpreting it differently: a lower-status job pushes the base model toward "true" and the post-trained model toward "false"; and 3) this flip is carried by a single residual-stream direction and happens at supervised fine-tuning. The mechanism was confirmed on 400 new claims with pre-specified predictions. None of seven deployed commercial models doubts lower-status posters more. Our work underscores the need to audit speaker bias per training recipe.

cs.AI · cs.CL · cs.CY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36888

Noise Steering: Exploiting Wake Steering and Acoustic Directivity for Noise-Constrained Wind Farm Control via Reinforcement Learning

Martín de Frutos, Baptiste Corban, Claire Bizon Monroc, Ana Bušić, Donatien Dubuc, Jiamin Zhud, Esteban Ferrer

原文摘要

Existing noise mitigation strategies for wind farms usually consist in reducing turbines power output, without accounting for the wake interactions between them and the noise emission directivity. This leads to over-conservative policies and unexploited wind power. Yet, turbine yaw can simultaneously affect wake interactions and the direction of noise emission, offering an additional degree of freedom for farm-level noise control. We therefore propose Noise Steering, a model-free reinforcement learning (RL) strategy that jointly controls turbine yaw angles and power setpoints to maximise farm power while satisfying a local noise constraint in a defined region. To enable training at a reduced computational cost, a low-fidelity acoustic model is coupled with the steady-state FLORIS simulator. The RL agent effectively learns how to redirect wakes and noise directivity away from the protected region while redistributing power across the farm. On a six-turbine test farm, the policy satisfies the 40 dB noise constraint throughout the full range of turbulent winds, with an average power deficit of only 2% relative to greedy unimpeded control, and up to 7.7% at high wind speeds. In comparison, the industry-standard noise-reduced operation (NRO) baseline here generates an average power loss of 17%. When deployed in the higher-fidelity FASTFarm simulator, the policy largely retains its performance under steady and turbulent inflow, despite differences in simulation fidelity. These results demonstrate the potential of combining yaw control and power derating through RL to improve the power-noise trade-off in wind farm operation.

cs.AI · eess.SY · physics.ao-ph · physics.flu-dyn

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38526

Value Probes: Learned Value Functions for Beam-Search Red Teaming

Jonathan F. Jao, Andrew Kyle Lampinen

原文摘要

Automated red-team auditing of language models is an important way to evaluate safety-relevant behaviors. These audits implicitly search a tree of possible conversation pathways: at each turn an auditor model decides which conversation to continue, and an LLM judge scores the dialogue. We emphasize that this auditing procedure is a Markov decision process, where states are the conversation history, actions are candidate responses, and rewards are judge scores for the target behavior. By adopting this perspective, we introduce two major improvements to auditing. First, we propose adopting beam search for the audit rather than relying on the auditor alone. We then interpret the problem of finding states that are likely to lead to problematic behavior as value estimation. Surprisingly, we show that this value function can be estimated by linear probing from the target model's activations to predict discounted future rewards - a method we term "Value Probes." By using Value Probes as a heuristic in our beam-search audit, we are able to substantially improve auditing success. Across 18 target behaviors and 3 scales of models, our approach raises peak audit scores by roughly 50% compared to (token-matched) standard auditing approaches. Furthermore, we show that Value Probes can be fit using off-policy data from smaller models. We also ablate individual components, and show that our method offers a comparably-performant and more efficient alternative to more expensive language model follow-ups. We hope these methods will improve language model auditing and lead to safer models.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2601.22118

Defining Operational Conditions for Safety-Critical AI-Based Systems from Data

Johann Maximilian Christensen, Elena Hoemann, Frank Köster, Sven Hallerbach

原文摘要

Artificial Intelligence (AI) has been on the rise in many domains, including numerous safety-critical applications. However, for complex systems in the real world, defining the underlying environmental conditions in which the AI-based system must operate---the Operational Design Domain (ODD)---is extremely challenging. This often results in an incomplete description of the ODD, which contrasts with the requirements of many domains for certifying AI-based systems. Traditionally, the ODD is created in the early stages of the development process, drawing on sophisticated expert knowledge and related standards. This paper presents a novel method for defining the ODD a posteriori from previously collected data using a multidimensional kernel-based representation. This approach is validated through both synthetic benchmarks and a real-world aviation use case. Moreover, the paper defines similarity of two ODDs if they generate the same outputs up to Lebesgue-null input sets and proves convergence in volume of the calibrated representation under the stated assumptions. The novel, safety-by-design, deterministic kernel-based ODD representation is derived fully automatically, given documented assurance inputs, permutation-stable, bounded by construction, and, under affine-equivariant per-dimension normalization, invariant to the choice of units. Utilizing the proposed ODD representation supports future certification of data-driven, safety-critical AI-based systems.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2605.00425

AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning

Haotian Zhao, Songlin Zhou, Yuxin Zhang, Stephen S. -T. Yau, Wenyu Zhang, Lun Tian, Tianshu Zhu, Yifeng Huang 等 12 位作者

原文摘要

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards provide limited guidance for assigning credit to individual steps within long interaction trajectories. Existing approaches often introduce dense intermediate supervision, such as process reward models or auxiliary self-supervised signals, which increases supervision and tuning complexity and may limit generalization across tasks and domains. We present AEM, a supervision-free credit assignment method that adaptively modulates entropy dynamics during RL training to improve the exploration-exploitation trade-off. Since in agentic RL the environment is typically affected by a complete response, rather than an individual token, our analysis lifts entropy dynamics from the token level to the response level, aligning uncertainty estimation with the effective action granularity of LLM agents and reducing sensitivity to token-level sampling noise. We further show that entropy drift under natural-gradient updates is governed by the interaction between the sampled-response advantage and its relative surprisal. Motivated by this result, AEM derives a practical response-level uncertainty proxy and uses it to rescale advantages, leveraging the evolving balance between positive and negative samples to naturally transition from exploration to exploitation. Extensive experiments on ALFWorld, WebShop, and SWE-bench-Verified with models ranging from 1.5B to 32B demonstrate that AEM consistently improves strong RL baselines, including a +1.4\% gain when integrated into a state-of-the-art software-engineering RL training framework.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2606.15735

EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries

Jiyoun Kim, Muhan Yeo, Eunhye Jang, Jeewon Yang, Hangyul Yoon, Su Ji Lee, Hee Jo Han, Hee-Jae Jung 等 17 位作者

原文摘要

Discharge summaries are crucial clinical documents containing the context of a patient's overall hospital stay, and are routinely reviewed by medical experts for patient readmission, ongoing care, and diagnostic decision-making. When reviewing them, medical experts often must iteratively synthesize information across multiple discharge summaries while verifying the evidence supporting each answer. Although large language models (LLMs) are increasingly explored for clinical question answering, existing benchmarks do not sufficiently reflect this setting: they often evaluate exam-style medical knowledge or focus on single-turn question answering with limited evidence-grounding evaluation. We introduce EHRNote-ChatQA, the first benchmark for evidence-grounded multi-turn clinical question answering over patients' multiple discharge summaries. Built from de-identified MIMIC-IV discharge summaries, EHRNote-ChatQA contains 967 patient-level multi-turn samples spanning one to five notes and 16,072 medical-expert-verified QA pairs (8,036 content questions, each paired with an evidence-grounding question) across eight clinical categories. The benchmark is constructed through an expert-informed pipeline combining discharge-summary structuring schema, expert-curated multi-turn QA templates, and LLM-based generation, followed by review and revision of every single QA sample by 12 medical experts (11 physicians and 1 nurse). Benchmarking 24 proprietary and open-weight LLMs reveals several challenges, including that LLMs struggle more with evidence grounding than content answering, multi-turn errors compound across turns, and single-turn clinical QA performance does not reliably transfer to this setting. These findings establish EHRNote-ChatQA as a rigorous and practical benchmark for evaluating clinical QA systems.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38517

AtomSteer: Test-Time Constraint Steering for Atomistic Generative Models

Pengfei Cai, Katharina S. C. Jäger, Utkarsh Utkarsh, Nofit Segal, Bowen Deng, Akshay Subramanian, Rafael Gomez-Bombarelli

原文摘要

Diffusion and flow matching models offer scalable approaches to generating crystalline materials, molecular conformers, and protein-ligand complexes. However, satisfying crystallographic symmetry, structural geometry, and accurate stereochemistry remains challenging. Satisfying these requirements calls for corrections that preserve the geometry already captured by the pretrained model. In this work, we propose AtomSteer, a test-time inference framework for steering pretrained atomistic generative models with structural constraints. During sampling, AtomSteer corrects intermediate structure predictions with bounded local projections, graph-rigid stereochemical transformations, and projections over periodic symmetries, accepting updates that improve constraint satisfaction while limiting changes to the rest of the structure. We demonstrate AtomSteer across three pretrained backbones, FlowMM, ET-Flow, and Boltz-2, spanning de novo crystal generation and crystal structure prediction, molecular conformer generation, and protein-ligand complex structure prediction. AtomSteer improves space-group distribution coverage in de novo crystal generation and improves target space-group recovery in crystal structure prediction. AtomSteer improves molecular validity and E/Z stereochemical accuracy while retaining conformer ensemble fidelity. For protein-ligand complexes, AtomSteer reduces ligand E/Z errors relative to experimental reference structures while achieving competitive docking success and PoseBusters validity. Our method provides a unified framework for adding chemical and crystallographic control to existing atomistic generative models without retraining or architectural changes.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.11447

Conditional Memory Enhanced Item Representation for Generative Recommendation

Ziwei Liu, Yejing Wang, Shengyu Zhou, Xinhang Li, Xiangyu Zhao

原文摘要

Generative recommendation (GR) has emerged as a promising paradigm that predicts target items by autoregressively generating their semantic identifiers (SID). Most GR methods follow a quantization-representation-generation pipeline. While most research focuses on quantization and generation, the representation that bridges the two remains underexplored. Existing representation constructions mainly take two forms: either directly flattening the SID code embeddings into a sequence or merging them into a compact vector via external networks. While effective, they still expose two practical challenges: \textbf{1) Loss of item semantics:} Information lost by quantization or compression needs to be recovered during the representation stage. \textbf{2) Insufficient modeling of structured SID relations:} Intra-item code composition patterns and inter-item prefix-transition patterns are not explicitly preserved for representation and subsequent SID generation. To overcome these challenges, we propose \textbf{ComeIR}, a \textbf{\uline{Co}}nditional \textbf{\uline{me}}mory Enhanced \textbf{\uline{I}}tem \textbf{\uline{R}}epresentation framework that reconstructs SID code embeddings into item-aware inputs and preserves structured SID evidence for prediction. Item-guided Token Scoring estimates the contribution of each SID code using the item embedding employed by the quantizer. Dual-level Conditional Memory captures intra-item prefix composition and inter-item prefix transitions, while Memory Merge integrates these signals into each historical item representation. The Memory-restoring Prediction Head further conditions SID-level prediction on the generated prefix and historical transition evidence. Extensive experiments demonstrate the effectiveness and flexibility of ComeIR, and further reveal scalable gains from enlarging conditional memory.

cs.IR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2605.26937

Beyond Questions: Evaluating the Stated Knowledge of LLMs

Luca Giordano, Simon Razniewski

原文摘要

Parametric knowledge in large language models (LLMs) is a cornerstone of their success, yet remains poorly understood. Existing knowledge benchmarks typically rely on predefined questions (e.g., "What is the birth date of M.L. King?"), evaluating only knowledge that benchmark designers explicitly choose to query, a problematic availability bias. In this paper, we introduce open knowledge evaluation, a new paradigm for benchmarking the stated knowledge of LLMs. Instead of asking narrow questions, it evaluates models on the knowledge they choose to surface in response to open-ended elicitation prompts (e.g., "Tell me everything you know about M.L. King"). This shifts the focus from predefined answer retrieval toward characterizing the knowledge models naturally express. We instantiate this paradigm with BeQu (Beyond Questions), a benchmark of 10,000 entities paired with reference corpora for statement verification. Using BeQu, we evaluate a broad range of language models and analyze the effects of reasoning effort, model scale, prompt format, and knowledge domain. Data and leaderboard are available on this work's GitHub repository and at bequ.scads.ai, the benchmark website.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.37708

Generative Interactions: Weaving Multiparty Human Motion with Bilevel Latent Dynamics

Ojas Shirekar, Yash Surange, Augustinas Jučas, Chirag Raman

原文摘要

Human social behaviour is not a collection of independent motions, but a jointly organised process in which group dynamics and individual variation continuously shape one another. Yet existing social motion models often prioritise plausible trajectories while leaving interaction state implicit, limiting their ability to transfer across groups, tasks, and partial-observation regimes. To address this gap, we introduce Bilevel Representations for Agent Interaction Dynamics (BRAID), a hierarchical sequential latent-variable model for generative multi-person interaction. BRAID explicitly formulates social motion generation as a meta-transfer learning problem: shared interaction priors are learned across datasets and adapted through arbitrary context sets of observed people and joints. The model represents each scene through a group-level latent state that captures shared interaction dynamics and person-level latent states that capture individual behaviour conditioned on the evolving group context. This modelling choice enables coherent generation under full, sparse, or partial observations while exposing compact social-state vectors that can serve as an interface for downstream embodied-agent systems. We evaluate BRAID under a unified SMPL-based representation on social forecasting, tracking and in-filling, and response generation, using metrics that assess not only reconstruction accuracy but also realism, diversity, temporal alignment, and interpersonal coordination. We further analyse the hierarchical latent space, showing that it captures separable group- and individual-level structure.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38508

SaiVLA-JEPA: Evaluating Future Latent Prediction in JEPA-Conditioned VLA Control

Rufeng Xiao, Ruihao Xiao, Wei Chen, Xinhai Sun

原文摘要

Joint-embedding predictive architectures (JEPAs) learn to predict representations rather than pixels, offering a compact way to model how visual scenes evolve. We ask whether this predictive objective improves closed-loop control when a vision-language-action (VLA) policy already uses V-JEPA features. We call our JEPA-conditioned flow policy family SaiVLA-JEPA. It combines a vision-language model with a diffusion transformer action expert and receives features from a frozen V-JEPA encoder. Two lightweight auxiliary heads predict future representations during training and are omitted at inference, leaving the action sampler unchanged. We compare policies without JEPA features, with current JEPA conditioning, and with additional future supervision on 10,030 paired LIBERO-Plus episodes. Current JEPA conditioning reaches about 82.5% success versus 71.6% without JEPA, while future supervision provides no detectable aggregate gain at the evaluated training budget. We separately evaluate SaiVLA-JEPA-TCA, which adapts latent context, and SaiVLA-JEPA-TPA, which adapts selected parameters. The context-retry gain is a system-level result under a larger attempt budget; parameter adaptation shows no consistent advantage over the frozen policy and target controls. These results motivate assessing latent-prediction objectives through paired closed-loop rollouts rather than latent loss alone.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.26480

FeatLens: Feature-Guided Dependency Retrieval for Repository-Level Code Generation

Xutian Li, Bo Xiong, Yifeng Zhu, Runbang Yan, Yanzhen Zou, Lu Zhang, Bing Xie

原文摘要

Retrieving task-relevant code dependencies is critical for repository-level code generation. Existing approaches obtain dependency context through similarity-based retrieval, repository graphs, or LLM-driven exploration. A central challenge is to identify the dispersed dependencies needed to implement a functional requirement, rather than merely retrieve broadly related code. This paper presents FeatLens, a feature-guided dependency retrieval approach for repository-level code generation. FeatLens first builds an offline index linking natural-language feature descriptions to function-level code entities. Given a task requirement and target function location, it selects relevant features and constructs dependency seeds. It then expands the seed graph and applies semantic and structural heuristics to select dependencies for inclusion in the generation context. Experiments on DevEval and EvoCodeBench show that FeatLens achieves the highest dependency recall among the evaluated baselines at each fixed retrieval budget, reaching DR@15 values of 0.527 and 0.529, respectively. On DevEval, the retrieved context supports the highest non-oracle Pass@1 with both DeepSeek-V3.2 and GPT-5-mini. These results are obtained without LLM calls in the online dependency retrieval stage.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.02004

ClueTracer: Question-to-Vision Clue Tracing for Training-Free Hallucination Suppression in Multimodal Reasoning

Gongli Xi, Kun Wang, Zeming Gao, Huahui Yi, Haolang Lu, Qianshan Wei, Ye Tian, Wendong Wang

原文摘要

Large multimodal reasoning models solve challenging visual problems via explicit long-chain inference: they gather visual clues from images and decode clues into textual tokens. Yet this capability also increases hallucinations, where the model generates content that is not supported by the input image or the question. To understand this failure mode, we identify \emph{reasoning drift}: during clue gathering, the model over-focuses on question-irrelevant entities, diluting focus on task-relevant cues and gradually decoupling the reasoning trace from visual grounding. As a consequence, many inference-time localization or intervention methods developed for non-reasoning models fail to pinpoint the true clues in reasoning settings. Motivated by these insights, we introduce ClueRecall, a metric for assessing visual clue retrieval, and present ClueTracer, a training-free, parameter-free, and architecture-agnostic plugin for hallucination suppression. ClueTracer starts from the question and traces how key clues propagate along the model's reasoning pathway (question $\rightarrow$ outputs $\rightarrow$ visual tokens), thereby localizing task-relevant patches while suppressing spurious attention to irrelevant regions. Remarkably, \textbf{without any additional training}, ClueTracer improves all \textbf{reasoning} architectures (including \texttt{R1-OneVision}, \texttt{Ocean-R1}, \texttt{MM-Eureka}, \emph{etc}.) by $\mathbf{1.21\times}$ on reasoning benchmarks

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.22399

Latent Style-based Quantum Wasserstein GAN for Drug Design

Julien Baglio, Yacine Haddad, Richard Polifka

原文摘要

The development of new drugs is a time-consuming and expensive process, with average costs estimated to be up to around $2.5 billion. The first step in this process is the design of the new drug, for which de novo drug design, assisted by artificial intelligence, has blossomed in recent years and has revolutionized the field. In particular, generative artificial intelligence has delivered promising results in drug discovery and development, reducing costs and time to solution. However, classical generative models, such as generative adversarial networks (GANs), can be difficult to train and are prone to mode collapse. Quantum computing may be an avenue to overcome some of these issues, providing compact models with far fewer trainable parameters, thereby enhancing the generalizability of GANs. We propose a new latent style-based quantum Wasserstein GAN (QGAN) for drug design, combining a variational autoencoder that maps molecular structures into a latent space with a hybrid quantum GAN. Our pipeline is benchmarked against classical models of the industry-relevant MOSES suite. Style-based noise reuploading at every rotational gate and a Wasserstein gradient penalty are used to improve trainability and to mitigate mode collapse. Training and large-scale sampling with circuits of up to 15 qubits are performed on noiseless quantum simulators to validate our architecture. We present an inference-only demonstration on an IBM Heron quantum computer using 5 qubits, sampling 2,500 new molecules, to investigate quantum noise effects. Our default QGAN, using 110 trainable generator parameters, reaches statistically comparable overall performance and statistically significant gains on selected drug-relevant metrics relative to both the MOSES classical latent GAN baseline, which contains about 700,000 trainable parameters for the generator, and a classical latent GAN with matched generator capacity.

quant-ph · cs.AI · cs.LG · q-bio.BM

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.28176

Temporal Evidence-Parameter Co-Alignment for LLM Reasoning over Temporal Knowledge Graphs

Jiapu Wang

原文摘要

Large Language Models (LLMs) often struggle with temporally grounded reasoning because their static parametric memory is misaligned with the dynamic evolution of real-world knowledge. Although RAG and Parameter-Efficient Fine-Tuning (PEFT) provide practical ways to enhance LLMs, they remain insufficient for temporal reasoning. Existing retrieval methods typically prioritize semantic relevance while overlooking temporal validity, event order, and evolutionary dependencies, resulting in evidence that is relevant in isolation but temporally fragmented. Meanwhile, conventional PEFT methods usually employ fixed and input-agnostic low-rank updates, making it difficult to capture time-dependent entity semantics and relation drift. To address these limitations, we propose Temporal Evidence-Parameter Co-Alignment (TEPCA), a framework for LLM reasoning over TKGs. TEPCA aligns LLM reasoning with temporal knowledge at both the evidence and parameter levels. At the evidence level, it introduces time-constrained Dynamic Relevance-Guided Path (DRGP) pruning to preserve globally coherent temporal paths, together with Mutual-Information (MI)-based pruning to retain query-informative local facts under temporal constraints. At the parameter level, it integrates Dynamic-Gated LoRA (DG-LoRA), a timestamp-conditioned low-rank adaptation mechanism that dynamically modulates the effective adaptation subspace according to temporal context. This design enables LLMs to better capture fine-grained entity evolution and time-dependent relation semantics while preserving parameter efficiency. Experimental results on two TKG benchmarks demonstrate that TEPCA achieves state-of-the-art performance. Additional evaluations of DG-LoRA on eight commonsense QA datasets further verify its general input-adaptive capacity, scalability across LLM backbones, and interpretability.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.08915

UniDG: Unified Defect Generation via Defect-Context Editing

Yuanting Fan, Jun Liu, Bin-Bin Gao, Xiaochen Chen, Yuhuan Lin, Zhewei Dai, Jiawei Zhan, Chengjie Wang

原文摘要

Generating realistic visual defects is crucial for alleviating the scarcity of abnormal samples in anomaly detection, yet existing methods often rely on category-specific few-shot adaptation and struggle to generalize across objects, defect types, and domains. This limitation stems in part from the lack of paired defect editing data and the fine-grained nature of defect appearance, where subtle variations in scale, texture, and morphology must be preserved while maintaining consistency with the target scene. To address this challenge, we introduce UDG, a dataset of 300K normal-abnormal-mask-caption quadruplets curated from diverse defect-related scenarios, and present UniDG, a unified defect generation model. UniDG formulates defect synthesis as Defect-Context Editing: it extracts reference defect context with adaptive cropping, organizes reference and target inputs in a structured diptych format, and fuses multimodal conditions through MM-DiT attention. We further develop a two-stage training strategy: Diversity-SFT learns diverse transferable defect priors from paired editing data, while optional Consistency-RFT can further improve reference adherence, local realism, and defect-category consistency. Without per-category fine-tuning or using MVTec-AD/VisA for training, UniDG outperforms prior few-shot anomaly generation and image insertion/editing baselines in both synthesis quality and downstream single- and multi-class anomaly detection/localization.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.06940

A First Guess Is Rarely the Final Answer: Learned Local Search That Generalizes to Larger Routing Problems

Andoni Irazusta Garmendia

原文摘要

Neural routing solvers rarely stop at their first solution: constructed tours are usually refined by search, such as sampling or local search. Neural improvement methods learn this search as a policy that repeatedly applies local moves, but existing policies degrade sharply beyond their training size. We argue that size generalization depends on whether the information that determines the value of a move reaches the policy in a size-independent form, and identify three places where existing policies fall short: the representation of the incumbent solution, the scale of the input features, and the computation of move gains. We address all three in NICO, a learned 2-opt policy for routing that represents the incumbent by its solution edges, one token per edge without positional encodings, describes them with scale-free features, and adds the exact gain of each move to its logit, so that the network learns a correction to greedy selection. A controlled factorial study shows that edge tokens outperform node tokens with positional encodings, that the exact gains are necessary for transfer in the tested configuration, and that scale-free features help only together with them. Trained on instances with at most 100 nodes, NICO reaches a 1.1% gap on the Euclidean TSP with 1000 nodes, against 10.7% for greedy 2-opt and 36% for the best prior learned policy. It also improves the tours of constructive and diffusion-based solvers, is the best improvement method on road-network costs, and on the CVRP outperforms every classical control.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38458

Tracekit Box: Running AI Agents in Micro-VMs Where Every Way Out Is Decided and Signed

Bravish Ghosh

原文摘要

AI agents now install packages, call model APIs with their operators' keys and change code in repositories that deploy to production. The network, credentials and write access they need are also how they can leak data, steal a key or change a system nobody approved. Sandboxes contain an agent but leave little evidence of what crossed their boundary; tracing records what happened but contains nothing. We present Tracekit Box, an open-source system (MIT, v0) that does both. Each job runs in its own Firecracker micro-VM with no network card. The only ways out are doors on the host, served over vsock: commands, outbound connections, secrets, model calls and the workspace patch. At every door a Tracekit signer the agent cannot reach decides what passes and signs it into one run per box. Names are resolved on the host; private and cloud-metadata addresses are always refused; secrets never enter the VM, which sees placeholders the host proxy swaps for real values only in one header for bound hosts; and changes come back as a patch applied file by file after the signer decides each file. Box fails closed, and each job ends as a .tkb bundle anyone can verify offline. All 13 end-to-end checks pass on a real KVM runner (the test that runs them takes 28.5 s, including image pull and boot); 15 fuzz targets on the trust boundary produced nine findings, all fixed; and the demo run's 102 signed records verify. Box does not yet run Firecracker's jailer, needs a co-located signer, and records processes inside the VM only where they cross a door.

cs.CE · cs.AI · cs.CR · cs.OS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.14326

ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation

Jungwoo Oh, Hyunseung Chung, Junhee Lee, Min-Gyu Kim, Hangyul Yoon, Ki Seong Lee, Youngchae Lee, Muhan Yeo 等 9 位作者

原文摘要

While Multimodal Large Language Models (MLLMs) show promising performance in automated electrocardiogram interpretation, it remains unclear whether they perform actual step-by-step reasoning or just rely on superficial visual cues. To investigate this, we introduce ECG-Reasoning-Benchmark, a novel multi-turn evaluation framework comprising over 6,400 samples to systematically assess step- by-step reasoning across 17 core ECG diagnoses. Our comprehensive evaluation of state-of-the-art models reveals a systematic shortfall in executing multi-step logical deduction. Although models possess the medical knowledge to retrieve clinical criteria for a diagnosis, they exhibit consistently low success rates in maintaining a complete reasoning chain, primarily failing to ground the corresponding ECG findings to the actual visual evidence in the ECG signal. These results demonstrate that current MLLMs bypass actual visual interpretation, highlighting a limitation in their visual grounding capabilities and motivating robust, reasoning-centric medical AI. The code and data are available at https://github.com/Jwoo5/ecg-reasoning-benchmark.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38448

Benchmarking decision models against generative large language models on medical multiple-choice questions

Oscar Freyer, Daniel Glauert, Moritz Hofmann, Max Ostermann, Stephen Gilbert, Jakob Nikolas Kather

原文摘要

Medical workflows often require selecting among predefined options. We compared 13 decision models with 15 generative large language model configurations, including different reasoning settings, using 1,273 four-option MedQA questions under text-only conditions. Accuracy ranged from 67.71% to 89.08% for decision models and from 78.32% to 96.86% for generative configurations. Among the tested configurations, Mercury Decide had the lowest mean final-attempt cost (USD 0.0069 per 1,000 questions), while Clef Omni had the shortest median request duration (0.291 seconds). Decision-model probabilities distinguished correct from incorrect answers, but error rates among answers assigned probabilities of at least 0.90 ranged from 1.71% to 12.77%. Answer agreement across three runs ranged from 92.30% to 100%, while probability repeatability varied. Decision models offered resource advantages alongside lower peak accuracy; selecting models for medical workflows requires considering probability quality and repeatability together with accuracy and the resources needed to detect and correct errors.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗