跳到正文
研踪PaperTrail

论文库

检索计算机领域论文，按研究方向、作者或关键词筛选。

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：2026-11-15 21:08 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-14 21:33 — 2026-11-15 21:33（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：2026-11-15 21:08最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,729 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 46 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-15 21:07（北京时间）
版本更新 · v2arXiv:2611.11854

Decoupled Asynchronous System for Humanoids (DASH): Latency-Agnostic Scaling of Vision-Language-Action Models for Humanoid Manipulation

Bingzhang Wang, Nathan Zhao, Jialeng Ni, Jiayin Zheng, Yin Zhang, Kehua Chen, Jian Yao

原文摘要

Vision-language-action (VLA) models pair a vision-language backbone with an action head, but in closed-loop control the backbone sits on the control-critical path: while it computes, the robot keeps moving, so each executed action is conditioned on an increasingly stale observation. A larger backbone therefore directly blocks reactivity, especially in humanoid dexterous manipulation. We present DASH, a Decoupled Asynchronous System for Humanoids that removes this coupling. DASH splits the policy into a slow vision-language model (System 2) and a fast flow-matching action head (System 1) that run as concurrent processes over the LCM communication protocol, so the control rate is set by the action head alone, independent of backbone size. The action head fuses stale semantics from a frozen backbone with fresh vision from its own ResNet encoder, desynchronized training exposes it to the staleness it meets at deployment, and an adaptive temporal aggregator aligns overlapping action chunks under variable inference latency. On an asynchronous RoboTwin benchmark that charges inference latency in simulated time, DASH holds 20 Hz control rate from 0.8B to 8B backbones while the synchronous rate falls from 9.7 to 4.1 Hz, with higher success at every size. On a real humanoid with dexterous hands, DASH achieves clearly higher pick-and-place success than the synchronous pipeline.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16184

Flow-CAD: Flow Matching for Contextual Anomaly Detection and Explanation in Tabular Data

Zhong Li, Qi Huang, Yuhang Wang, Yang Cao, Thomas Bäck, Niki van Stein, Matthijs van Leeuwen, Lincen Yang

原文摘要

Contextual anomaly detection in tabular data aims to identify objects whose behavior is unexpected under their contextual conditions. In data-engineering pipelines, this task screens table rows whose measurements violate context-dependent integrity relationships. Most existing approaches rely on either shallow conditional models with limited distributional expressiveness or localized estimators that require per-context modeling, making it difficult to capture complex conditional relationships and scale to high-dimensional settings. We propose Flow-CAD, a new framework for contextual anomaly detection based on Flow Matching. Flow-CAD learns a single global and amortized conditional generative model that flexibly represents behavioral distributions conditioned on context, without assuming simple parametric forms or retraining local models. To enable robust and interpretable anomaly scoring, we introduce a scale-normalized and truncated residual energy derived from the learned conditional flow, which stabilizes anomaly scores, mitigates domination by extreme deviations, and supports feature-wise attribution. We further provide theoretical insights showing that the proposed residual-based anomaly score is stable under velocity estimation error, and that its Monte Carlo estimator satisfies concentration bounds. Experiments on 20 benchmark datasets with 13 competitors demonstrate that Flow-CAD has the best average rank for PR AUC, ROC AUC, and P@n, highlighting its effectiveness and practicality for contextual anomaly detection in tabular data. We provide the source code at https://github.com/ZhongLIFR/FlowCAD.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15276

Verify by Doing: Co-Evolving Agent Execution and Evaluation without External Feedback

Yitong Lin, Jianda Chen, Yihao Hu, Pan Wang, Hang Wang, Zhihao Wen, Xiaoxue Ren, Wei Wu

原文摘要

Agent self-improvement requires feedback about task success, yet external feedback may be unavailable at test time. Agents must then infer success from observable evidence, and incomplete verification can misguide subsequent updates. We introduce Verify by Doing (VbD), a method that co-evolves Actor and Evaluator harnesses within a single task while keeping model weights fixed. The Evaluator actively inspects artifacts and environment state with tools; its findings ground an internal signal for output selection and guide updates to both execution and verification procedures. Proposed Evaluators undergo comparative review on common candidates, while Actor updates require support from their own fresh outputs. Across AutomationBench, $τ^3$ Banking, and selected GDPval tasks, VbD achieves the highest overall scores among the compared methods operating without external feedback, with gains of 3.3, 4.1, and 2.3 percentage points over the strongest baselines on the main backbone. Ablations support the contributions of active verification and Evaluator evolution, and selection from fixed candidate pools shows that improved verification can recover successful outputs without generating new ones.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15109

Expanding the Decision Space of Pretrained Models through Structured Re-Decoding

Tinglan Wang, Qun Su, Shihang Wang, Chi Wang, Lin Wang, Shaobo Chen, Haixu Liu, Hai Wei 等 14 位作者

原文摘要

Native decoders limit how pretrained models combine local predictions under new structural constraints. We introduce Structured Re-Decoding (SRD), a training-free framework that constructs local candidates from model scores, samples, or external specifications, jointly optimizes their selection, and verifies reconstructed outputs. We show that candidate recombination expands feasible support and can improve attainable reward under a fixed KL divergence budget. Across molecular generation, protein design, RNA structure prediction, and antibody modeling, SRD enables improved structured inference, including verified molecules absent from the original sample pool. External chemical templates further extend SRD to noncanonical amino acids, peptide cyclization, and grammar-guided molecular construction. Preliminary experiments on a physical coherent Ising machine demonstrate the feasibility of hardware-based optimization, suggesting broader opportunities for quantum and quantum-inspired approaches to structured inference and combinatorial optimization across scientific domains.

cs.AI · q-bio.BM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15013

Protecting Sensitive Knowledge Under LLM Unlearning: The Proxy Threat and a Superposition-Aware Defense

Jiayang Li, Tianqing Zhu, Longxiang Gao, Huajie Chen, Dayong Ye, Shang Wang, Huan Huo, Wanlei Zhou

原文摘要

Machine unlearning lets the owner of large language models (LLMs) remove specific entities from a trained model without retraining from scratch. Existing machine unlearning methods focus on removing the requested entities while maintaining utility. However, we observe that the representations of distinct entities in an LLM may overlap in shared parameter subspaces, a phenomenon known as knowledge superposition. Removing one entity may then affect other entities. This exposes a new security threat: legitimate unlearning requests can be exploited to remove sensitive entities that were never requested. This threat is unlike data poisoning or backdoor attacks. We define the attack as the Proxy Unlearning Attack (PUA), which selects removable proxy entities superposed with a sensitive target. The attack can even occur unintentionally, when benign users accidentally remove entities superposed with a sensitive one. In response, we propose Superposition-Aware Unlearning Protection (SAUP), a general defense framework that can be applied to unlearning requests to ensure a correct removal. SAUP performs in two stages. Before unlearning, it uses superposition detection to estimate which sensitive entities the request puts at risk. After unlearning, it decouples the shared representations and restores the affected entities, while keeping the requested entities suppressed. Our findings reveal that legitimate unlearning requests can be maliciously exploited through knowledge superposition. When dealing with unlearning requests, LLM providers need representation-level detection and recovery mechanisms to mitigate this threat and protect sensitive knowledge.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14978

Hijacking a Trusted LLM in Real-World Quantized Deployments Only Requires a Disguised Adapter

Jiayang Li, Tianqing Zhu, Huan Huo, Heng Xu, Shang Wang, Wanlei Zhou

原文摘要

Third-party low-rank adaptation (LoRA) adapters are tailored to perform decision tasks such as content moderation and function selection. However, in the real world, quantized deployments carry a potential threat in that an adapter can pass an audit with the unquantized base, yet hijack decisions when the same base is quantized for deployment. Demonstrating this threat requires an adapter that preserves benign behavior before quantization, but hijacks decisions afterward. Further, this must hold without modifying the trusted base or knowing the victim's quantization configuration. We therefore present QHijack-LoRA, an adapter-only attack that uses the base model's natural quantization residual to activate decision hijacking. The attacker modifies neither the trusted base model nor the victim's quantization configuration. With QHijack-LoRA, a four-objective training procedure separates full-precision dormancy from quantized target activation, while preserving clean-input behavior. The adapter is trained across several different quantization methods, while adaptive reweighting and residual-direction augmentation extend the attack to unseen configurations. Our results show that auditing performed exclusively under full-precision conditions does not provide assurance of decision integrity in quantized deployment environments. Thus, we also propose a cross-precision paired audit that checks the candidate adapter in its intended deployment configuration. This work shows the critical need to audit third-party adapters in any potential quantized deployment.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14491

TimeSeek：面向泛化时间序列分析的多任务多领域预训练

TimeSeek: Multi-Task and Multi-Domain Pretraining for Generalized Time Series Analytics

Peng Chen, Yihang Wang, Zhongwen Rao, Yang Shu, Yuying Qiu, Yuxuan Chen, Lujia Pan, Bin Yang 等 9 位作者

AI 速读 基于摘要

提出统一预训练模型 TimeSeek，通过多领域特征提取与多任务协同训练，提升时间序列预测、异常检测和分类的泛化能力。

cs.LG

arXiv ↗PDF ↗
查看原文摘要

Time series analytics has been widely applied across various domains. While existing time series foundation models (TSFMs) have demonstrated promising results, they still face two major challenges: 1) Most TSFMs mainly rely on stacking Transformer layers to increase parameter size, lacking the ability to adaptively model complex time series patterns from multi-domain data. 2) Current TSFMs are primarily pre-trained for specific tasks, e.g., forecasting or anomaly detection, and a few models support multiple tasks, but they fail to fully leverage task specificity and commonality, resulting in suboptimal performance. To address these challenges, we propose TimeSeek, a novel generalized time series analytics model that adaptively models time series patterns from multi-domain data and unifies multiple tasks in pre-training. Conceptually, TimeSeek is guided by selective information sharing under domain and task heterogeneity. From the perspective of multi-domain data, we propose a Multi-Domain Feature Extractor that adaptively captures temporal dependencies and channel correlations based on domain-specific characteristics, including progressive multi-scale modeling and adaptive slot channel modeling. From the perspective of the diversity of tasks, we propose multi-task collaborative training, which leverages task specificity and task commonality through task customization and cross-task training, effectively unifying multiple tasks in pre-training and better adapting to diverse downstream scenarios. After pre-training on large-scale time series data, TimeSeek achieves state-of-the-art performance in forecasting, anomaly detection, and classification tasks across both few-shot learning and zero-shot situations, together with favorable inference efficiency.

版本更新 · v2arXiv:2609.36630

A Comprehensive Survey of Agent Distillation across Models, Artifacts, and Harnesses

Ziluowen Luo, Senzhang Wang, Chaozhuo Li, Jun Yin, Hao Yan, Ming Cheng, Chenxu Wang, Songyang Liu 等 13 位作者

原文摘要

Knowledge distillation provides a teacher-student framework for transferring capabilities at reduced cost and has been widely studied for large language models (LLMs). As LLM-based agents move from response generation to sustained, closed-loop task solving, distillation expands beyond model parameters to knowledge retained in reusable resources and execution workflows. This shift from model-level to agent-level knowledge transfer supports efficient deployment, broader capability access, and continual self-evolution. However, existing surveys largely examine model distillation and agent system design separately, limiting comparison of transfer strategies across agent components. To bridge this gap, we formalize Agent Distillation as persistent knowledge transfer between teacher and student agents and present its first unified survey. Distinguishing experience used for transfer from knowledge retained for reuse, we develop a knowledge-substrate taxonomy based on where knowledge persists: models, artifacts, or harnesses. Building on this taxonomy, we analyze cross-substrate transfer paths and hybrid strategies. To assess the resulting capabilities, we review benchmarks and evaluation protocols for retention, causal attribution, and deployed utility without further teacher support. This survey provides a unified basis for studying agent knowledge transfer and developing efficient, adaptable, and self-evolving agents.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.06931

Science Edge Evaluation: SEE the Missing Step Toward Real Scientific Discovery

Taolin Han, Yuchen Zhang, Jinghang Wang, Yun Wu, Wai Yuet Chiu, Zhaohai Li, Yifei Zhang, Jinxin Wang 等 25 位作者

原文摘要

Large language models (LLMs) are increasingly involved in scientific discovery, yet it remains unclear whether they can support complex real laboratory science. Here we introduce Science Edge Evaluation (SEE), a multimodal benchmark of expert-curated questions grounded in peer-reviewed literature and experimental practice in chemistry, biology, and materials science. Evaluation of 28 multimodal large language models (MLLMs) shows that even the best-performing model reaches only 54.9% accuracy. Moreover, general-purpose models outperform science-specialized models on average. In the visual-agent evaluation, the use of tools increases the best accuracy to 56.1%. Tool use can expand the information available to models, but more information does not necessarily lead to reliable scientific reasoning. The key challenge is whether models can manage tool-derived information within the boundaries of the original experimental evidence. Together, these findings reveal that current MLLMs still cannot reliably make justified and evidence-bounded inferences from experimental results, which is an essential capability in real scientific discovery. Bridging this gap requires MLLMs to transition from explaining established scientific concepts to deriving novel and evidence-based insights from experimental data.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11856

DeltaForge: A Post-hoc Mixture-of-Experts VLA for Multi-Domain Autonomous Driving

Bingzhang Wang, Mo Poorsartep, Yasaman Esfandiari

原文摘要

Fleets of driving vision-language-action (VLA) models are developed one domain at a time: each operator finetunes a shared base model on private data, producing specialized experts that are costly to consolidate into a single model. Weight merging loses accuracy as heterogeneous domains accumulate, and dense mixture-of-experts routing is prohibitively expensive to combine them. We present DeltaForge, to our knowledge the first post-hoc mixture-of-experts VLA for driving, which consolidates N independently finetuned per-domain models into a single multi-domain model from their weights and a small proxy set alone. When different operators finetune the same base model, their weight updates end up sharing a lot of structure. We exploit this by decomposing all the updates together using singular value decomposition (SVD), splitting each one into a shared part (the same across all domains) and a tiny domain-specific part. The router then only needs to work with those tiny domain-specific pieces, not the full expert weights, which is what keeps the approach efficient. Then two cooperating clip-level blind routers, one over the VLM reasoning experts and one over the flow-matching dynamics experts, are trained from soft labels on the proxy dataset. Across six diverse domains spanning urban, off-road, and highway driving on cars, trucks, and all-terrain vehicles (ATVs), DeltaForge approaches the accuracy of the per-domain experts and surpasses every merging, routing, centralized, and federated baseline at close to single-model parameter and compute cost. Adding a new domain requires only projecting its weight update onto the shared basis with no end-to-end retraining needed. The resulting model also generalizes to domain combinations it was never explicitly trained on.

cs.LG · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11560

LiveAsset: Learning Intent Assets from Corrective Interactions for Agent Runtime Control

Guanming Liu, Weihang Wang, Peng Zhang, Meng Wu, Kainan Tu, Jiahao Liu, Yu Zhang, Liuxin Zhang 等 11 位作者

原文摘要

Large language model (LLM) agents acting across web applications and online services often need multi-turn corrections to align their work with users' underspecified goals and preferences. In practice, users may identify problems in the current outcome without specifying the desired result, so learning user intentions requires interpreting each correction against the agent's preceding and revised outcomes. These expectations are often connected to a particular context, making it hard to know when they apply and how to ensure the agent later acts as the user expects. To this end, we propose LiveAsset, an intent harness that learns reusable intent assets from corrective interactions and uses them for runtime control of agent execution. LiveAsset jointly interprets each correction with the agent's original and revised results to infer user intent, incrementally updating the assets while preserving earlier requirements that remain applicable. The learned requirements guide agent execution from task entry and provide criteria for runtime verification, which uses the explanations to assess applicability before each reply is delivered and directs the agent to revise the result to address unmet requirements while preserving those already satisfied. Following a learning phase in which simulated users progressively reveal requirements through multi-turn corrections, we evaluate LiveAsset using same-task replay of the original requests on π-Bench, PERMA, and Vita and cross-task transfer on PAST-Bench and SkillEvolBench. Experiments show that LiveAsset better fulfills requirements learned from corrective interactions and improves performance on these benchmarks compared with memory, skill, and rule-based harness baselines. Code is available at github.com/landian60/LiveAsset.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10542

When Experience Becomes a Backdoor: Poisoning Self-Evolving LLM Agents via Failure-Aware Task Optimization

Minhua Lin, Zongyu Wu, Hanqing Lu, Xianfeng Tang, Xiang Zhang, Qi He, Suhang Wang

原文摘要

Large language model (LLM) agents increasingly improve themselves through self-evolution, distilling execution experience into persistent, reusable skills. However, this persistence creates a new attack surface: malicious rules implanted into skills can compromise subsequent agent behavior. Existing skill backdoor attacks typically assume direct manipulation of the victim's skills, which is impractical when skills are constructed internally by a trusted evolver. In this paper, we study a novel problem of task-level backdoor attacks, where the attacker can only inject poisoned evolution tasks, inducing the agent to implant backdoors into its own skills. Since the attacker controls neither skill induction nor downstream execution, a natural approach is to iteratively optimize poisoned tasks based on attack success. However, our preliminary analysis reveals two key challenges: (i) failures at different stages of skill evolution and downstream execution can produce indistinguishable outcomes, providing little guidance for targeted poisoned-task updates; and (ii) unsuccessful updates may undermine earlier progress, while simply discarding them may lead to repeated ineffective updates. To address these challenges, we propose BadEvolve, a failure-aware task-poisoning framework against self-evolving LLM agents. BadEvolve diagnoses attack failures across four stages, i.e., Induction, Activation, Following, and Effect, and directs updates toward the failing stage. It further employs rollback to preserve earlier progress and failure memory to avoid repeating ineffective updates. Extensive experiments across diverse self-evolution frameworks, benchmarks, and backbone LLMs demonstrate the effectiveness of BadEvolve. Our code is available at https://github.com/ventr1c/BadEvolve.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08798

Driver Takeovers and Longitudinal Responses Analysis from Naturalistic Driving

Yuhang Wang, Hao Zhou

原文摘要

As Level 2 advanced driver-assistance systems (ADAS) become more widely used, understanding driver-system interaction is increasingly important for traffic safety. However, limited real-world data make these interactions difficult to study. We present ADAS-TO, a naturalistic dataset of 16,446 takeover clips from 364 drivers across 2,585 different drives. It combines road video, vehicle kinematics, driver inputs, and ADAS status. To analyze takeover behavior, we retained 6,206 manually reviewed takeover events during continued lane keeping or car following. We excluded events in which the driver intentionally changed lanes, turned, or made a stop beyond the ADAS's capabilities (e.g., at a red light or stop sign) shortly after takeover. Drivers began intervening before ADAS disengaged in 65.6% of takeovers involving braking or steering. When the ego vehicle was still closing on a lead vehicle at disengagement, longitudinal safety margins often narrowed further after the transfer to manual control. Among 2,031 such events, 78.5% had a lower minimum time-to-collision (TTC) in the five seconds after disengagement than in the five seconds before it. For events involving braking, the mean TTC trajectory reached its minimum about 1.2 s after disengagement. We model the subsequent braking response using a Gazis-Herman-Rothery (GHR) car-following law. Its median five-second spacing root-mean-square error is 1.34 m with observed lead motion and 1.84 m with predicted lead motion. The fitted model expresses braking as a response to looming, with stronger responses at higher speeds and shorter gaps. Applied before takeover, it shows that greater looming than predicted by the human-response reference is associated with disengagement. These findings support continued assessment of longitudinal safety after ADAS disengagement, while the driver's braking response develops.

cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.20424

BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business

Enhan Zhao, Yongqi Tong, Xuejun Yu, Hang Wang, Pan Wang, Yichao Wang, Di He, Jianshe Li 等 10 位作者

原文摘要

Existing long-horizon agent benchmarks often emphasize final task success while providing limited assessment of intermediate execution validity. Yet real-world business operations require agents to navigate extensive, potentially outdated or conflicting policies while satisfying critical constraints throughout execution. These requirements are particularly consequential in high-stakes domains such as payments, where intermediate violations can incur financial losses or regulatory consequences regardless of the final outcome. To bridge this evaluation gap, we introduce BizAgentBench, a multi-turn benchmark grounded in real-world procedures from a leading payments company. Its executable environment integrates 789 knowledge documents and 601 discoverable business tools, with consistent policies, states, and tool behavior. The benchmark comprises 50 tasks involving resource constraints, temporal dependencies, prior commitments, and conflicting or outdated guidance. Each task is validated through reference execution, while deterministic checks assess both goal attainment and execution validity without prescribing a single solution path. Experiments reveal substantial limitations even among frontier models: Claude Opus 5 and GPT-6 Sol achieve strict success rates of only 64.0% and 61.3%, respectively. For Qwen3.8-27B, goal attainment reaches 42.0%, but strict success drops to 32.7%, demonstrating how outcome-based evaluation can mask invalid execution. Beyond success rates, DeepSeek-V4.1-Flash averages 191.3 tool calls per run, approximately 70% more than reference executions, revealing substantial execution overhead. Overall, BizAgentBench establishes a testbed for evaluating and advancing long-horizon agents beyond task completion, toward reliable and constraint-compliant execution in complex business environments.

cs.CE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.14571

StreamMemBench: Streaming Evaluation of Agent Memory for Future-Oriented Assistance

Guanming Liu, Yuqi Ren, Hansu Gu, Peng Zhang, Weihang Wang, Jiahao Liu, Ning Gu, Tun Lu

原文摘要

A central role of personal-agent memory is to turn stored information and prior interactions into future-oriented assistance. In daily use, useful cues come from what the agent observes and how the user interacts with the agent, and the agent must carry them forward from the current request to similar future tasks. Existing memory benchmarks usually test dialogue recall or task improvement in isolation, leaving the trajectory from streaming observations to later assistance largely untested. We introduce StreamMemBench, a streaming benchmark that constructs a two-step task sequence around each evidence anchor from EgoLife egocentric streams. The initial task tests evidence use, while the follow-up task tests whether feedback and interaction experience are reused. Four metrics diagnose evidence recall, initial evidence use, feedback incorporation, and follow-up reuse. Experiments with eight memory systems across two backbones show that current systems often fail to use observed evidence or turn feedback into reliable follow-up behavior, even when evidence is stored or feedback is incorporated locally. StreamMemBench is publicly available at https://github.com/landian60/StreamMemBench.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.21569

Decoupled Safety Control: A Safety-Control Algorithm for Training-Free Safety Guidance

Huilin Zhou, Ruoxi Cheng, Yuhang Wang, Yuming Liu, Minghao Sun, Ruolong Ma, Lan Zhang

原文摘要

Diffusion models achieve strong performance in text-to-image generation, but they can still produce unsafe content. Training-free safety guidance offers a practical inference-time alternative that intervenes during sampling without modifying model weights. However, many existing safeguards still rely on a coupled safety-control chain. In this chain, the same unsafe condition simultaneously specifies what should be avoided, indicates the current unsafe signal, constructs the intervention, and determines when that intervention remains active. This coupling can work when unsafe factors are explicit, but becomes less reliable once harmful and benign semantics are entangled in the current generation state, often leaving residual unsafe content or unnecessarily degrading benign-generation quality or prompt fidelity. We address this problem with Decoupled Safety Control (DSC), a plug-in safety-control algorithm for training-free safety guidance. DSC reformulates training-free safety guidance as an explicit state-dependent control process, so the executed intervention is determined from the current generation state rather than inherited directly from a single unsafe condition. Experiments on standard safety benchmarks show that DSC improves representative latent- and text-space safeguards, achieving stronger unsafe-content suppression while preserving benign-generation quality and maintaining efficient inference.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.00359

Position: Agentic Evolution is the Path to Evolving LLMs

Minhua Lin, Hanqing Lu, Zhan Shi, Bing He, Rui Mao, Zhiwei Zhang, Zongyu Wu, Xianfeng Tang 等 15 位作者

原文摘要

As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with continual deployment environment change. Scaling training-time and inference-time compute improves static capability but does not close this train-deploy gap. We argue that addressing this limitation requires a new scaling axis-evolution. Existing deployment-time adaptation methods, whether parametric fine-tuning or heuristic memory accumulation, lack the strategic agency needed to diagnose failures and produce durable improvements. Our position is that agentic evolution represents the inevitable future of LLM adaptation, elevating evolution itself from a fixed pipeline to an autonomous evolver agent. We instantiate this vision in a general framework, A-Evolve, which treats deployment-time improvement as a deliberate, goal-directed optimization process over persistent system state. We further propose the evolution-scaling hypothesis: the capacity for adaptation scales with the compute allocated to evolution, positioning agentic evolution as a scalable path toward sustained, open-ended adaptation in the real world. Our code is publicly available at https://github.com/A-EVO-Lab/a-evolve.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.30621

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

Minhua Lin, Juncheng Wu, Zijun Wang, Zhan Shi, Yisi Sang, Bing He, Zewen Liu, Tianxin Wei 等 17 位作者

原文摘要

LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task execution without changing model parameters. Harness self-evolution adapts such agents by updating these harnesses from execution evidence. Yet it remains unclear whether a model's base capability in task-solving predicts its capabilities in harness self-evolution: which models produce useful harness updates, and which actually benefit from them? We analyze two harness self-evolution capabilities: (i) harness-updating, the capability to produce useful persistent harness updates from execution evidence; (ii) harness-benefit, the capability to benefit from updated harnesses during task solving. Our analysis reveals two findings. First, harness-updating is flat in base capability: models from different capability tiers produce harness updates that lead to surprisingly similar gains; even Qwen3.5-9B's updates yield gains comparable to those of Claude Opus~4.6. Second, harness-benefit is non-monotonic in base capability: weak-tier models benefit little from updated harnesses, mid-tier models benefit most, and strong-tier models benefit less than mid-tier. We trace low gains at the weak tier to two failure modes: weak-tier models may fail to activate relevant harness artifacts, or activate them but fail to follow them faithfully. These findings suggest investing capability budget in the task-solving agent rather than the evolver, and targeting harness invocation and long-horizon instruction following in agent training. Our source code is publicly available at https://github.com/A-EVO-Lab/a-evolve/tree/release/harness-evolution.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06120

ReactWorld: Structuring Interaction Responses for Embodied Video Generation

Hanwei Liu, Huijia Zhang, Hanzhang Wang, Guangyu Liu, Hanbei Zhan, Linjie Hu, Bin Xiao, Xuan Zhou 等 9 位作者

原文摘要

Embodied video world models predict scene changes caused by robot actions, yet generated object responses may remain inconsistent with task intent and contact dynamics. Critical responses in embodied scenes often concentrate in local regions and specific time intervals. Inspired by chain-of-thought reasoning, we introduce ReactWorld, an embodied video generation model guided by structured interaction anticipation. In the generation backbone's feature space, an interaction response field predictor anticipates how the interaction will unfold, explicitly describing participant roles, future motion response intensity, and local motion changes. A response feedback adapter forms increments to object features from the difference between the object branch's outputs with predicted and zeroed local dynamics inputs. It also converts predicted displacements into positional biases for temporal attention. These two mechanisms guide object feature updates and information retrieval across frames, respectively. Through interaction anticipation and generative feedback, ReactWorld achieves an average score of 77.51 on RBench, outperforming PhysisForcing by 3.29 points with improvements in all nine categories. On EZS-Bench, it achieves a Domain score of 86.98 and an average score of 81.87.

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.26516

Algorithmic Principles For Multiclass Learning Are Hard To Come By: Limits of Regularization and Proper Learning

Julian Asilis, Shaddin Dughmi, Vatsal Sharan, Alec Sun, Shang-Hua Teng, Chang Wang

原文摘要

Two of the most fundamental questions in statistical learning theory are the following: which prediction problems are learnable, and how should they be learned? For the former, elegant answers often take the form of combinatorial dimensions. The latter question, however, has proved considerably more elusive: all known general-purpose multiclass learners rely on intricate orientations of exponentially large one-inclusion structures, and familiar algorithmic principles such as proper learning and regularization remain poorly understood. Motivated by prior work, we ask whether learning reduces to proper learning---possibly over a larger hypothesis class---and whether proper or improper multiclass learning can ultimately be captured by suitable regularizers. Our primary results answer both questions negatively, resolving three open problems from prior work. First, we exhibit a learnable multiclass problem that cannot be embedded in any properly learnable class, meaning learning cannot be reduced to proper learning by enlarging the hypothesis class. Second, we demonstrate that proper learning can require training error and characterize this phenomenon precisely: every properly learnable class admits a proper learner making $o(m)$ errors on samples of size $m$, but every prescribed sublinear scale $a_m=o(m)$ is necessary for some properly learnable problem. Third, regularization is not a general learner: we exhibit a properly learnable class that cannot be learned by any Structural Risk Minimization (SRM) learner, and a learnable class that cannot be learned by any local regularizer. We complement these impossibility results with a positive theory that gives two sufficient conditions for SRM learnability and characterizes SRM representability through integrability of revealed preferences.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04603

SCANO: Restoring Boundary-Condition Completeness in Sampled Meshes with a Sliced-Cross-Attention Neural Operator for 3D Thermal Fields

Tianyu Li, Zhiwei Cao, Qingang Zhang, Ruihang Wang, Binyang Song, Yonggang Wen

原文摘要

Training neural operators on million-cell meshes can exceed GPU memory limits. Models are therefore trained on subsamples and deployed on whole meshes or selected regions. However, subsampling can distort boundary information, degrading accuracy. We ask when boundary conditioning under sampling stays consistent with whole-mesh training, and how to aggregate and inject boundary data. Representing the solution as an integral of boundary data against type-dependent measures, we show that subsampling distorts this conditioning in three ways: incomplete boundary coverage or a sample-dependent global state, face weighting by count rather than area, and compression of boundary inputs into a low-dimensional vector. This analysis yields four measurable consistency conditions checkable before training. We satisfy them with two backbone-agnostic modules. Boundary Quadrature Attention (BQA) aggregates all boundary faces, typed and area-weighted, into slice tokens that every query point reads at every layer. Anchored Global State (AGS) estimates the global state from anchors independent of the sampled points. Adding both to a scalable message-passing and slice-attention backbone yields SCANO. We evaluate the approach on controlled and public benchmarks and a data-centre thermal simulation dataset (DCTS) containing million-cell meshes. On both benchmarks, BQA improves every backbone, reducing whole-mesh error up to 15-fold. On all three datasets, AGS aligns regional with whole-mesh predictions, cutting regional error at least tenfold for most backbones on the public benchmark. Together, the modules nearly halve the best original backbone's whole-mesh error on both benchmarks. SCANO predicts a room-scale field in under one second, over 100 times faster than whole-room anchor self-attention.

cs.LG · physics.comp-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02491

Same Sentence, Different Construct: Identity-Swapped Rationales Reveal Measurement Non-Invariance in LLM Hate Speech Classifiers

Wenchang Wang, Yue Song

原文摘要

Large language models are increasingly used as measurement instruments for socially consequential constructs such as hate speech, and are typically validated by their aggregate agreement with human labels. A valid instrument must also apply the same construct to every group it measures. We test this requirement using 421 \hc{} templates that are instantiated identically for seven protected groups, so that only the identity term varies. Four LLM classifiers each exceed 0.95 balanced accuracy, yet within identical templates two of them miss hateful statements about women at markedly higher rates than the same statements about other groups (excess false-negative rates of 8.3 and 4.4 percentage points), a gap first reported for fine-tuned classifiers in 2021. We show how the construct shifts. Comparing rationales within each template, we find that models invoke protected-group status for other groups but recast the identical statement about women as personal dislike or as aimed at an individual, in 22 of 30 missed templates for one model. Adding the benchmark's own definition, which lists sex as a protected characteristic, does not close the gap, and the contrast persists. Apparent false-positive disparities, by contrast, largely vanish under identity control and trace to reclaimed slurs present only for some groups. Errors shared by all models concentrate where model and benchmark definitions diverge, and pairwise counterfactual accuracy adds little beyond endpoint accuracy. We argue that validating LLM measurement requires identity-controlled tests of measurement invariance that examine both decisions and the criteria models state for them.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.23344

Language Models Learn to Improve Language Models

Minhua Lin, Zijun Wang, Zewen Liu, Zhaotian Weng, Bing He, Zhan Shi, Benoit Dumoulin, Xiang Zhang 等 10 位作者

原文摘要

Large language models (LLMs) are increasingly used to automate AI research, including language-model (LM) development, offering a potential path toward recursive self-improvement. However, turning experimental feedback into a learned ability to propose effective improvements across models faces two challenges. First, training such an ability with real feedback is expensive: reinforcement learning (RL) requires evaluating tens of thousands of proposals, each potentially requiring a full model-training run. Even at ten GPU-hours per run, reward collection alone would consume hundreds of thousands of GPU-hours, motivating a cheaper surrogate. Second, surrogate feedback can become unreliable as policy optimization favors overestimated proposals when the proposal distribution shifts. To address these challenges, we propose LM2LM, which trains LLMs with RL to generate effective LM improvement proposals. To provide scalable feedback, we use a research world model (RWM), a frozen LLM that predicts proposal gains from real experimental records provided in context, as the reward model for RL. To maintain feedback reliability, we periodically execute current-policy proposals ranked highly by the RWM and add their measured outcomes to its context. Across eight autoregressive and diffusion LM development environments, real-execution evaluations on held-out tasks show that LM2LM enables Qwen3.8-27B to outperform GPT-6-sol, even when GPT-6-sol is given 300 real experimental records in context, while requiring 33% lower data-generation cost. LM2LM also generalizes to a model family unseen during training.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02273

When the Text Is Silent: Memory Shortcuts and the Validity of LLM Annotation under Evidence Insufficiency

Wenchang Wang, Yue Song

原文摘要

Large language models (LLMs) are increasingly used to annotate text for social science research, content moderation, and training data. Their broad knowledge of real-world entities raises a concern: when labeling a text, do they rely on its evidence or substitute what they already know? We call this behavior a memory shortcut and examine when it emerges, what amplifies it, and how to mitigate it. Using 995 widely recognized public figures and four matched control names per figure, we construct counterfactual texts that separate textual evidence from prior knowledge, and evaluate three commercial LLMs on 121,594 prompts each across five stages. We find a striking asymmetry. Although all models recognize nearly every figure, none follows memory over the text when the two conflict. Shortcuts instead emerge when evidence is absent: for one model, famous names raise the rate of remembered occupations, ages, and countries by 17.0, 14.9, and 6.8 percentage points relative to synthetic names. These effects occur only for recognized figures, and 98.6% of the resulting labels are factually correct about the namesake while none is supported by the text. Evaluation threats and answer-contingent rewards amplify shortcuts by 8.7 and 12.4 points. Famous names also raise leadership ratings of sparsely documented applicants by 0.22 and 0.28 points in two models. A namesake reminder and name masking each eliminate the shortcuts, with trade-offs in gender annotation. LLM annotations can thus be factually correct yet methodologically invalid. Trustworthy LLM annotation requires audits that test evidence absence, account for incentives in annotation instructions, and evaluate the attribute-specific trade-offs of mitigation.

cs.HC · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01715

EarlySelectKV: Anticipatory KV Selection via Cross-Layer Query Proxies

Yuhao Liu, Yuehao Li, Linghe Zhang, Gaobin Huang, Junran Li, Hongchang Wang, Haifang Jian

原文摘要

Query-conditioned sparse KV selection reduces long-context inference cost by attending to a subset of historical KV entries at each decoding step. Existing selectors must wait for the target-layer query before scoring candidates and generating indices, placing routing on the immediate pre-attention path. We introduce EarlySelectKV, a training-free transformation that uses proxy queries from earlier hidden states to precompute selected KV indices while retaining the real target-layer query for final attention. Tests with RocketKV, Quest, and Loki show no consistent pattern of quality degradation across the evaluated settings. In the primary RocketKV evaluation, ES-RocketKV differs by +0.018 points on LongBench, approximately -0.01 points on RULER, and +0.25 percentage points on representative NIAH/Passkey settings. In a TensorRT-LLM deployment with CPU-offloaded routing, ES-RocketKV improves end-to-end output throughput by up to 12.4% and reduces GPU-resident memory by 11.1% of the combined KV/K-summary pool. This makes routing timing an explicit optimization target alongside KV subset selection in sparse long-context decoding. Code is available at https://github.com/sea-with-sakura/EarlySelectKV.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.07598

Mapping the Emerging Social Science of Large Language Models

Zhanzhan Zhao, Yi Yang, Xiao Jia, Zeyun Dong, Chenzhang Wang

原文摘要

As large language models (LLMs) blur the boundary between cognition and computation, they reshape knowledge production and collective life. We combine a curated review of 198 papers with computational mapping of 47,719 formally published papers from five databases. Text embeddings, clustering, and topic modeling organize the curated literature into 13 subcategories across three domains. LLM as Social Minds examines mind-like reasoning and socially grounded behavior in individual models. LLM Societies explores how interactions among agents produce collective behavior and social organization. LLM-Human Interactions examines how people perceive and engage with LLMs, and how interaction reshapes human thinking, creativity, and relationships. Structural topic modeling of the larger corpus traces how research attention shifts over time and differs across publication venues. We present a reproducible framework that identifies the field's underlying structure and enables its continuous refinement as new studies emerge. The review also identifies a gap in current understanding: the mechanisms underlying many of LLMs' observed cognitive and social behaviors remain unclear. Human-like performance can then be mistaken for understanding, obscuring the norms, biases, and structures of power that LLMs reproduce. We call for shared benchmarks and robustness checks across the three domains to build a reliable evidence base for understanding LLMs' social behaviors and informing their design and use.

cs.CY · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.19098

TAU-R1: Visual Language Model for Traffic Anomaly Understanding

Yuqiang Lin, Kehua Chen, Sam Lockyer, Arjun Yadav, Mingxuan Sui, Shucheng Zhang, Yan Shi, Bingzhang Wang 等 15 位作者

原文摘要

Traffic Anomaly Understanding (TAU) is important for traffic safety in Intelligent Transportation Systems. Recent vision-language models (VLMs) have shown strong capabilities in video understanding. However, progress on TAU remains limited due to the lack of benchmarks and task-specific methodologies. To address this limitation, we introduce Roundabout-TAU, a dataset constructed from real-world roundabout videos collected in collaboration with the City of Carmel, Indiana. The dataset contains 342 clips and is annotated with more than 2,000 question-answer pairs covering multiple aspects of traffic anomaly understanding. Building on this benchmark, we propose TAU-R1, a two-layer vision-language framework for TAU. The first layer is a lightweight anomaly classifier that performs coarse anomaly categorisation, while the second layer is a larger anomaly reasoner that generates detailed event summaries. To improve task-specific reasoning, we introduce a two-stage training strategy consisting of decomposed-QA-enhanced supervised fine-tuning followed by TAU-GRPO, a GRPO-based post-training method with TAU-specific reward functions. Experimental results show that TAU-R1 achieves strong performance on both anomaly classification and reasoning tasks while maintaining deployment efficiency. The dataset and code are available at: https://github.com/siri-rouser/TAU-R1

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.30238

SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data

Wenhao Li, Zhibin Wu, Chong Xiao, Qiangchang Wang

原文摘要

Recent research on Multimodal Sentiment Analysis (MSA) has focused on learning from language, visual, and acoustic modalities with incomplete data to infer human sentiment. Most studies typically compensate for missing information by reconstructing modality features or designing complicated fusion mechanisms. However, these methods still suffer from spurious generation and noisy guidance due to the lack of high-level semantic grounding in partially observed multimodal evidence. To address these issues, we propose SemMSA, a latent semantic-aided framework that constructs rich sentiment-relevant semantics with LLMs, fully integrating with all modalities via anchor-free spectral alignment. It mainly consists of Cross-modal Semantic Refinement (CSR) and Cross-modal Spectral Alignment (CSA). Specifically, CSR first adaptively extracts visual and acoustic representations by corresponding adapters to form a unified multimodal prefix with language in the frozen LLM embedding space. It then iteratively produces continuous discriminative semantic states through a token-efficient latent refinement process without decoding explicit text. Next, CSA simultaneously aligns the refined semantics with all modalities by enhancing the dominant spectral component of their kernel Gram matrix. This captures global nonlinear dependencies among all representations without relying on a predefined anchor modality. In addition, an instance-level spectral separation constraint preserves cross-sample discriminability and mitigates representation collapse. Extensive experiments on SIMS, MOSI, and MOSEI benchmarks demonstrate that SemMSA achieves state-of-the-art performance.

cs.CL · cs.CV · cs.MM

查看论文
arXiv ↗PDF ↗
版本更新 · v6arXiv:2505.11037

Diffusion-based Evolutionary Optimization for 3D Multi-Objective Molecular Generation

Ruiqing Sun, Dawei Feng, Sen Yang, Ronghang Wang, Huaiyuan Song, Bo Ding, Yijie Wang, Huaimin Wang

原文摘要

De novo 3D molecular design with multiple properties and fragment-retention constraints is formulated as a constrained multi-objective optimization problem. Existing 3D diffusion models provide strong capabilities for generating novel molecules, but adapting them to new conditions and multi-objective optimization tasks remains difficult. We present Diffusion-based Evolutionary Molecular Optimization (DEMO), a framework that draws solely on the unconditional molecular prior of a frozen pretrained diffusion model to generate chemically valid 3D candidates, while evolutionary search handles conditional generation and constrained multi-objective optimization, without retraining or fine-tuning. DEMO performs crossover and mutation on intermediate diffusion states through an Evolutionary-Guided Diffusion (EGD) operator, combines 2D topology and 3D geometry in Structure-Aware Environmental Selection (SAES) to preserve structural diversity, and uses three cooperating populations to coordinate structural exploration, fragment-constraint satisfaction, and property optimization. Experimental results demonstrate that EGD outperforms task-specific conditional generators in property targeting; SAES preserves structural diversity while retaining competitive hypervolume in multi-objective optimization; and DEMO improves objective convergence and generates diverse feasible molecules under fragment constraints. These results show how evolutionary search can reuse existing diffusion models for diverse molecular design requirements.

cs.NE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.05521

Reasoning from Traces: Divergence-Guided Agentic Repair of WebAssembly Discrepancies

Liyan Huang, Kaicheng Wang, Amy Zhang, Weihang Wang

原文摘要

WebAssembly (Wasm) promises seamless reuse of C/C++ codebases as portable, efficient, sandboxed binaries for execution on the Web. In practice, however, this promise often falls short: recent studies show that cross-compiling C/C++ source to Wasm and native binaries frequently produces runtime discrepancies due to differences in library implementation and compiler bugs. Since the root causes are platform-level and hidden beneath the source code, even state-of-the-art LLM-based coding agents can struggle to diagnose and repair these discrepancies. In this paper, we present WasmMend, the first system for automatically repairing Native-Wasm functional discrepancies. WasmMend transforms open-ended debugging into a two-stage process. First, a novel differential trace analysis approach localizes the function where Wasm and native executions first diverge. Second, guided by this localization, a multi-agent system coordinates separate agents to interpret platform-specific behavior and synthesizes patch plans. Experiments on discrepancies from real-world C/C++ projects show that, across five backbone models, WasmMend achieves a fix rate of up to 84.8%, with average gains of at least 37.2 percentage points over the evaluated open-source coding agent baselines, while maintaining comparable cost.

cs.SE

查看论文
arXiv ↗PDF ↗