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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 14:26 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 14:46 — 2026-11-09 14:46（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 14:26最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 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 3,653 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 14:25（北京时间）
版本更新 · v2arXiv:2511.17671

Cross-User Poisoning: User-Task Boundary Failures in Multi-User Collaborative Language Agents

Atharv Singh Patlan, Peiyao Sheng, S. Ashwin Hebbar, Prateek Mittal, Pramod Viswanath

原文摘要

Language agents are moving from single-user assistants to shared collaborators in workspaces, forums, and group chats. A shared agent observes interleaved messages from multiple users, maintains persistent context, and executes tool actions, creating a boundary problem absent from standard single-user agents: the agent must decide not only whether an instruction is safe, but which user or task it is allowed to govern. We identify cross-user poisoning (CUP), where an adversary injects a message into shared context that is later applied while the agent serves a benign user, causing unauthorized actions or responses outside the instruction's intended scope. We validate CUP on two deployed multi-user agents, Continua and ElizaOS, and introduce MURMUR, a framework for evaluating shared-context agents under concurrent multi-user interactions. Across Slack, Workspace, and Airline domains, CUP achieves high attack success, persists across later interactions, and remains substantially more effective than matched prompt-injection attacks. We evaluate boundary-scoping defenses and find that context summarization alone is insufficient, while task clustering and provenance prompting substantially reduce non-adaptive propagation. These results show that robust multi-user agents require explicit user/task scoping rather than generic input filtering or context compression.

cs.CR · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36135

Physical structure as an organizing principle for universal Hamiltonian learning

Mingkang Liu, Zhanghao Zhouyin, Guanghui Wang, Daye Zheng, Lei Shen, Qiangqiang Gu

原文摘要

Density functional theory (DFT) gives the electronic structure of materials, but its cost limits large-supercell calculations and materials screening. Machine-learned Hamiltonians bypass the self-consistent cycle but are usually system-specific; universal ones could cover new compositions and disordered solids. Such models must generalize across chemistry and keep downstream properties physical, while staying inexpensive for large cells. Here we introduce UniTB, a universal E(3) equivariant Hamiltonian representation framework that integrates physical priors rooted in density-functional tight-binding theory with deep learning. UniTB's network, which corrects a prior Hamiltonian, generalizes across chemistry through a mixture of experts routed by that prior and a charge-equilibration head as in self-consistent-charge tight binding. A projection bounds band shifts from the prior, suppressing spurious states and keeping downstream properties physical. We provide the fastest SO(2) tensor-product GPU kernels for the network. The variant UniTB-Flash assembles its prior from two-center tables at $O(N)$ cost for $N$ atoms, against $O(N\log N)$ on a grid. Trained on 29,242 crystals, UniTB reaches a 0.48 meV matrix-element error on nonmagnetic test crystals spanning 68 elements. Without amorphous training data, both models agree with DFT optics and conductivity of amorphous Ge-Sb-Te. UniTB-Flash ranks candidates with no significant difference from UniTB, whose property values are more accurate; together they screen 16,195 crystals for five application domains of industrial relevance.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36134

When Connectivity Misleads: Guiding Agentic Search with Contrastive Evidence Paths

Junchen Li, Liang Xu, Rongzheng Wang, Qizhi Chen, Junhao Wen, Shuang Liang

原文摘要

Search agents can use cross-document graphs to discover sources through multi-hop connections and choose subsequent actions based on candidate rankings and relationships within a limited observation window. However, documents may rank highly because their numerous connections make them easier to reach, without necessarily providing more valuable evidence. Graph diffusion methods such as Personalized PageRank (PPR) aggregate propagation contributions from multiple sources, allowing highly connected distractor nodes to crowd the observation window. Flat node scores also obscure cross-document evidence trails, limiting continued exploration. We propose Contrastive Evidence Paths (CEP), which scores candidates by their strongest individual paths on a query-conditioned document graph and calibrates these scores against the same graph's background visitation distribution to mitigate structural bias. CEP ranks candidates by the calibrated scores and retains the corresponding source paths. Building on CEP, we develop Structured Corpus Interaction (SCI), which organizes candidates and their connecting paths into a structured Map, enabling agents to verify source documents and pursue missing information through expansion from anchor documents. Experiments on BrowseComp-Plus and TREC-COVID show that SCI achieves state-of-the-art answer accuracy and nDCG@10 with the lowest generation cost. Compared with the strongest baselines by task performance, maximum reductions in tool calls and total generation costs exceed 50% and 40%, respectively. Further analysis confirms that SCI with CEP suppresses ranking inflation induced by structural connections and improves gold recall and exploration efficiency.

cs.IR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.12856

Moderation by Interrogation: Uncovering Concealed Intent in Agent Social Networks

Ali Al-Lawati, Nafis Tripto, Abolfazl Ansari, Fali Wang, Jason Lucas, Suhang Wang, Dongwon Lee

原文摘要

The emergence of multi-agent systems introduces novel moderation challenges that extend beyond content filtering. Agents with $\textit{malicious intent}$ may contribute content that appears benign to evade content-based moderation, while serving a hidden objective. To address this challenge, we introduce Bot-Mod a moderation framework that grounds detection in agent intent rather than traditional content-level signals. Bot-Mod interrogates a target agent using a fixed set of diagnostic probes and infers its intent through Bayesian posterior inference over candidate intents. It starts with a calibrated content-only prior and updates the posterior using the $\textit{likelihood}$ of each answer under every candidate intent, as assigned by the moderator, until a stopping criterion is met. To evaluate our approach, we construct Molt-Intent, a dataset derived from Moltbook, capturing diverse benign and malicious behaviors within real community structures through posts and comments. Across Molt-Intent, an external social engineering dataset, and three agent LLMs, Bot-Mod outperforms content-only moderators, a fine-tuned classifier, and judge-based interrogators both in- and out-of-distribution. On Molt-Intent, it reaches a composite F1 of 0.736 in distribution and 0.684 out of distribution, 22% and 14% above the best baseline.

cs.AI · cs.SI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.00087

DeGenTWeb: A First Look at MGT-dominant Websites

Sichang Steven He, Calvin Ardi, Ramesh Govindan, Harsha V. Madhyastha

原文摘要

Many news reports have claimed that machine-generated text (MGT) from large language models (LLMs) is taking over the web. However, these claims are typically not based on a representative sample of the web, and the methodology underlying them is often opaque. Consequently, we lack an understanding of the true prevalence and characteristics of MGT on the web. We describe DeGenTWeb, which systematically identifies MGT-dominant websites: sites whose informational prose content is mostly MGT, with little human input. We show how to adapt detectors of MGT for use on web pages, and how to aggregate detection results from multiple pages on a site for accurate site-level categorization. DeGenTWeb mislabels only 0.12% of human-authored sites as MGT-dominant. We find that 20.9% of the sites archived by Common Crawl between January and July 2026 and 13.6% of the sites linked from Bing's search results in 2025 are MGT-dominant. These figures are lower bounds on the prevalence of MGT-dominant sites. We also find that the fraction of MGT-dominant sites is growing over time, and that many such sites share the same owner. We will release all of our code and data after publication.

cs.NI · cs.AI · cs.CY · cs.IR · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.09410

RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models

Weijia Liufu, Xiaoyu Guo, Ruiyi Chen, Jingzhi Liu, Kaidong Zhang, Xiwen Liang, Jianqi Lin, Dawei Sun 等 19 位作者

原文摘要

Vision-Language-Action (VLA) models remain brittle in long-horizon, contact-rich manipulation because success-only imitation provides little supervision for execution drift, while failed rollouts are often discarded. We introduce RePO-VLA, a recovery-driven policy optimization framework that assigns distinct roles to success, recovery, and failure trajectories. RePO-VLA first applies Recovery-Aware Initialization (RAI), slicing each corrective suffix into a new episode so corrective actions depend on the current adverse state rather than the preceding failure. It then learns a Progress-Aware Semantic Value Function (PAS-VF), aligning spatiotemporal trajectory features with instructions and successful references. The resulting labels salvage useful failure prefixes via reliability decay, while low-value labels mark drift and terminal breakdowns, teaching differences among nominal, failed, and corrective actions. The data engine turns adverse states into planner-generated or human-collected corrective rollouts, teaching recovery to the success manifold. Value-Conditioned Refinement (VCR) trains the policy to prefer high-progress actions. At deployment, a fixed high-value token biases actions toward the learned success manifold without online failure detectors or heuristic retries. We introduce the Failure-Recovery Benchmark (FRBench), with standardized error injection and recovery-focused evaluation. Across simulated and real-world bimanual tasks, RePO-VLA improves robustness, raising adversarial success from 20% to 75% on average and up to 80% in scaled real-world trials. Code and video results are available at https://1018weijia.github.io/RePO-VLA-Web/.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36116

Why and How to Do Science When AI Is Better at It: A Framework Grounded in Human Understanding and Direction

Hoda Heidari, Aydin Mohseni

原文摘要

As AI begins to match or exceed human researchers at core scientific tasks, two questions become pressing: \emph{why} should humans keep doing science, and \emph{how} should they use AI when they do? This paper argues that the second can be answered only by answering the first. It holds that one indispensable aim of science is \emph{durable, collective human understanding of the world, pursued in service of human ends and values}. From this principle it derives a two-part test for when a research task can be delegated to AI. The first part, \emph{human understanding}, requires that the scientific community remain able to explain, defend and contest the resulting claims, and retain the skills to do so. The second, \emph{human direction}, requires that judgments about which questions matter and what findings mean stay with accountable humans. Applying the test to each phase of research in the Contributor Roles Taxonomy (CRediT) yields recommendations that fields can tailor to their questions and methods. The framework differs from existing guidance in three ways. It rests on an account of what science is for rather than on integrity norms. It holds even if AI outperforms human researchers, rather than depending on AI's current limitations. And it judges each use of AI by its effects on human understanding and direction rather than by the type of tool, across every phase of research, including peer review and the training of new researchers. It closes with the reforms needed to keep science aimed at human understanding and direction.

cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36114

Context Is a Pipeline, Not a Window: Information Attrition in LLM Agent Harnesses

Yuvraj Sehgal, Mahsa Panahandeh, Naser Ezzati-Jivan

原文摘要

LLM agents are judged by two numbers: the size of the context window, and how often the final answer is correct. Both numbers miss a third thing: how much of a tool's output is lost before the model ever sees it. We measured this loss in a real tool-using agent. The agent finds the cause of injected faults by reading Linux kernel traces. The context window was almost empty: across 720 runs, the single largest prompt used only 5.75% of it. Yet a third of all tool results (3,827 of 11,189) were cut before they reached the model, and every cut result became broken JSON. The harness cut each result by slicing its JSON text at a fixed length. This does not shorten a result evenly. It deletes whatever data sits near the end. One field reached the model in only 4.7% of calls. A second field, in the very same results, reached the model in 99.3% of calls. Which field held the fault's evidence depended on when the faulty process started: early or late in the trace. The agent's diagnosis accuracy matched this same split. So we ran controlled experiments to test one question: did the data loss cause the drop in accuracy? This paper makes four contributions. First, we model an agent's context as a five-stage pipeline, with a measured failure at each stage. Second, we replay 864 real tool results, including one from a production trace where the shipped cut deletes all 128 records of the fault's evidence. Third, a controlled experiment shows that the cut's real cost appears first as extra work, not as wrong answers: 43% more tool calls, twice the computation, and yield falling from 0.61 to 0.31. The agent still finds the right answer when it has another way to reach it. Fourth, a survey of seven agent frameworks finds two that cut tool output the same unsafe way. Whether the data cut truly causes the accuracy drop is still an open question.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.22793

Reach-Avoid Differential game with Reachability Analysis for UAVs: A decomposition approach

Minh Bui, Simon Monckton, Mo Chen

原文摘要

Reach-avoid (RA) games have significant applications in security and defense, particularly for unmanned aerial vehicles (UAVs). These problems are inherently challenging due to the need to consider obstacles, consider the adversarial nature of opponents, ensure optimality, and account for nonlinear dynamics. Hamilton-Jacobi (HJ) reachability analysis has emerged as a powerful tool for tackling these challenges; however, while it has been applied to games involving two spatial dimensions, directly extending this approach to three spatial dimensions is impossible due to high dimensionality. On the other hand, alternative approaches for solving RA games lack the generality to consider games with three spatial dimensions involving agents with non-trivial system dynamics. In this work, we propose a novel framework for dimensionality reduction by decomposing the problem into a horizontal RA sub-game and a vertical RA sub-game. We then solve each sub-game using HJ reachability analysis and consider second-order dynamics that account for the defender's acceleration. To reconstruct the solution to the original RA game from the sub-games, we introduce a HJ-based tracking control algorithm in each sub-game that not only guarantees capture of the attacker but also tracking of the attacker thereafter. We prove the conditions under which the capture guarantees are maintained. The effectiveness of our approach is demonstrated via numerical simulations, showing that the decomposition maintains optimality and guarantees in the original problem. Our methods are also validated in a Gazebo physics simulator, achieving successful capture of quadrotors in three spatial dimensions space for the first time to the best of our knowledge.

eess.SY · cs.AI · cs.GT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36113

Scaling and Renormalization in Neural Networks: An Effective Renormalization-Group Description of Grokking

Min Chen, Junqi Wang, Zeguan Wu, Wenhao Huang, Junyu Liu

原文摘要

Grokking is a delayed transition from memorization to generalization in deep neural networks (NNs). We examine whether scaling and renormalization group (RG) theories can describe this dynamics, establishing a quantitative physical framework for neural generalization transitions. For modular addition on a two-layer NN, an ensemble of trained models defines an order parameter (the squared weight norm) and fluctuation proxies for the heat capacity and the susceptibility, with training epoch and weight decay serving as thermal and field control coordinates. To bridge neural architectures to real-space RG, we construct an exact coupling matrix via a second-order expansion of the loss with respect to per-neuron norms and use its Fiedler vector to define an effective geometry. This spectral ordering yields a monotonic spatial decay of coupling strength that is absent under random permutations. We then execute real-space RG by block-spin aggregating adjacent neurons and parameterizing the coupling matrix into off-diagonal band strengths. Linearizing this local RG map yields relevant scaling exponents and five derived critical exponents, with direct empirical estimates matching RG predictions within 1-10%. Overall, our framework provides a consistent effective description of grokking, suggesting the scaling and renormalization group formalism as a tool to investigate NN dynamics.

cs.LG · cs.AI · hep-th · quant-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36110

Dirichlet Process Mixtures within Semiparametric Bayesian Networks: A Novel Conditional Density Estimation Approach

Victor Alejandre, Pedro Larrañaga, Concha Bielza

原文摘要

Semiparametric Bayesian networks (SPBNs) are flexible probabilistic graphical models for representing joint distributions of continuous variables through lower-dimensional conditional probability distributions (CPDs). Existing SPBN models use kernel density estimators (KDEs) for non-parametric CPD modeling, but their one-component-per-observation mixture representation can lead to increased inference costs and density estimation errors, which can be limiting. In this work, we define a new CPD modeling approach for non-parametric components based on Bayesian non-parametric Dirichlet Process Mixtures (DPMs) within SPBNs. DPMs provide a data-adaptive clustering of observations, yielding a more compact representation while retaining the flexibility of non-parametric density estimation, unlike KDE. This results in lower inference costs while improving density estimation performance. We implement the proposed DPM-based SPBN (DPM-SPBN) by extending the open-source PyBNesian package and evaluate it on synthetic and real-world data. For a given network structure, DPM-based CPDs significantly outperform state-of-the-art Bayesian network models for continuous variables in density estimation, achieving lower absolute log-likelihood errors on synthetic data. We further investigate the impact of the proposed CPD modeling on structure learning methods relying on CPD-based scores. DPM-based SPBNs achieve lower structure learning and density estimation errors than KDE-based SPBNs. Experiments on real-world data corroborate these findings, identifying DPM-based CPD modeling as the most effective alternative among the evaluated non-parametric approaches for continuous variables.

cs.LG · cs.AI · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36108

Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol

Yuepeng Hu, Chongyu Fan, Sirat Samyoun, Jian Du

原文摘要

LLM agents increasingly access external tools through the Model Context Protocol (MCP), but the natural-language metadata used to describe those tools creates a prompt-injection surface. Within this established tool-poisoning surface, we study Log-To-Leak, an additive post-hoc logging attack that induces a separate attacker-controlled call after the final legitimate call. Its payload targets the user query, MCP server name, server response, and agent response. We operationalize the injected directive through Trigger, Tool Binding, Justification, and Pressure, and separately measure call success, payload fidelity, and preservation of legitimate behavior. We evaluate five MCP servers and four LLM agents using five metrics spanning effectiveness, utility, and efficiency. Across 18 model-server pairs with valid tool execution, Log-To-Leak achieves an attack success rate (ASR) of 62.64-100% and conditional logging accuracy (LA) of 76.55-95.64%; 16 pairs have absolute target-task completion changes of at most 6.63 percentage points. Three evaluated defenses leave residual ASR above 55% on GitHub MCP with GPT-4o, while an instruction detector flags 85.53% of benign descriptions. These results show that successful task completion can coexist with unauthorized post-hoc disclosure and motivate host-controlled authorization for secondary tool calls.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36100

CohortFlow: A Steerable Clinical Cohort Curation Agent with Localized Semantic Correction

Neil Chen, Adrian Serapio, Hanxue Gu, Evan Lee, Kang Wang, Yang Yang

原文摘要

Language model agents for clinical cohort curation should accommodate evolving eligibility criteria without repeatedly processing unchanged requirements. We introduce CohortFlow, a steerable agent that represents natural language corrections as localized updates to a structured cohort specification and reconciles them with a persistent execution graph. Explicitly recorded semantic dependencies enable affected computations to be selectively invalidated while preserving valid prior results. On 100 scenarios derived from clinical-trial eligibility criteria, comprising 126 correction turns, localized steering achieves 77.0% requirement micro-F1 versus 76.4% for full regeneration using the same 8B model, a small numerical advantage that is not statistically significant ($p=0.493$). It reduces mean correction latency by 64.8% after completion and 44.3% during execution, with 38.1% fewer model calls. In a separate proof-of-concept evaluation over MIMIC, all 13 cohort states execute successfully, while correction trajectories demonstrate selective preservation of unaffected computations and recomputation of changed or dependent nodes. Together, these results show that localized semantic steering can substantially reduce correction latency and model calls while maintaining strong requirement-level accuracy.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36082HF 社区推荐

How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning

Johnny Yu, Cyril Gorlla

原文摘要

Financial institutions operating under data-residency constraints are restricted to open-weight models small enough to locally host, which trail frontier systems on multi-step quantitative reasoning. On-policy distillation narrows such gaps by supervising a student on its own rollouts, but traditional OPD requires a strong external teacher, and on-policy self-distillation (OPSD) conditions on a full reference solution. We ask how much of that signal is necessary. We present Fin-SD, a localized hindsight self-distillation recipe for multi-step reasoning. Given a problem the student fails, the student itself identifies the first incorrect reasoning step and writes a short critique of that step. We truncate the student's trajectory immediately before the error (aiming to obtain a correct prefix), condition a frozen copy of the student on the same prefix plus the hint, and distill that hint-conditioned teacher into the student over a short rollout under reverse KL. No external model contributes a gradient. We apply Fin-SD to GPT-OSS-20B on a custom multi-step financial reasoning benchmark that requires deriving formula inputs from realistic scenarios via accounting conventions. We find: (i) replacing the critique with a generic-feedback control matches Fin-SD's entire 3.03 pp accuracy gain over the base model on the FinanceReasoning Hard subset, suggesting the gain comes from where supervision is applied, not hint content; (ii) the model writing the hint does not need to be stronger than the model receiving it: hints from same-family GPT-OSS-120B, at roughly 6x the parameters, yield no materially greater benefits than self-written hints; and (iii) Fin-SD matches on-policy self-distillation from full reference solutions on accuracy while generating 9.5% fewer tokens. With Fin-SD, general reasoning on MMLU-Pro and a fourteen-metric compliance audit on FinTrust show no material regression.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36077HF 社区推荐

The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents

Weidong Tang, Ruiheng Wang, Jingxuan Zhang, Hexin Wang, Haoyuan Chen, Zhengfeiyang Zhang, Yixing Ma, Zichen Jiang 等 20 位作者

原文摘要

Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous, verifiable environments is costly, and manual Harness iteration cannot keep pace with growing task diversity and complexity. A key insight is that tasks with different modalities and surface forms can share the same underlying capability requirements. We therefore introduce The Trinity, a recursive self-improvement framework coupling world generation with Harness evolution through three roles: Creator, Explorer, and Evolver. Drawing on verified execution trajectories, Evolver shifts the basis of task organization from surface categories to shared requirements, reorganizing the original task tree into a hierarchical capability tree. We introduce Capability-Driven Real2Sim2Real: for heterogeneous tasks at the same node, Creator abstracts their common requirements into simplified, verifiable simulated worlds for capability learning, while evaluation on original tasks measures transfer. Along this capability tree, Explorer progressively evolves reusable capability modules through selective inheritance, forming a Harness tree whose validated updates accumulate across iterations within a fixed topology. The resulting Harnesses specialize in different capabilities, motivating a Capability-Aware Harness Router that uses public task information to select compatible module configurations from the tree. Our evolved Harnesses improve mean performance by 34 points across 28 training benchmarks and 26 points across 18 unseen benchmarks, including two real-world embodied tasks.

cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36068HF 社区推荐

Rollback: Experience Backtracking in World Models for Policy Improvement

Jiayi Luo, Yang Zhang, Liliang Chen, Nan Wang, Chen Gao, Boxiang Qiu, Zhuoxuan Li, Baorui Peng 等 16 位作者

原文摘要

Action-conditioned world models offer a scalable alternative to costly real-world interaction for improving robot policies. However, existing world-model-based methods largely treat world models as forward-only surrogates of the physical environment, leaving untapped a capability no physical environment affords: rewinding to past decision points to explore counterfactual futures. We introduce Rollback, a policy improvement paradigm that turns world models from passive simulators into counterfactual engines: it rolls back to critical decision points, branches into alternative actions, and contrasts their outcomes to attribute success to individual decisions. This concentrates imagination where it matters most and distills counterfactual outcomes into fine-grained, action-level supervision without a separately learned value model. We build a scalable training system that unifies distributed world-model search with asynchronous real-robot execution, forming a self-reinforcing cycle: real-world experience continually sharpens the world model, and a sharper world model in turn drives further policy improvement. We term the world-model side of this cycle test-time physics grounding, a capability that hand-built physics simulators lack: while the world model serves as the training environment, real transitions from the policy it trains correct its dynamics through a lightweight LoRA pipeline. Experiments on three challenging real-world tasks show that Rollback improves success rates over the strongest baseline by an absolute 10.67%, 11.11%, and 11.85% on block extraction, ball tossing, and tabletop curling, respectively, while achieving more stable improvement throughout training. Although initialized from teleoperated demonstrations far below human level, Rollback surpasses the average success rate of human players on both ball tossing and tabletop curling within 8 hours of training.

cs.RO · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35868

Retriever-Free Retrieval: Navigating Documents with Decision Models

Chao Wan, Paul Jünger, Beixi Du, Bodong Liu, Navaneetha Krishnan, Kilian Q. Weinberger

原文摘要

While language models have become dramatically more capable, retrieval still largely relies on lexical matching or similarity in fixed embedding spaces. This creates a capability asymmetry: what the retriever fails to find, even the strongest generator cannot recover. We propose DecisionRAG, which brings the capabilities of pretrained language models to retrieval using decision models that jointly evaluate candidate branches in a single forward pass, without generating any tokens, and show that judging candidates in a shared context makes their relevance estimates comparable. Like a person browsing a library, DecisionRAG navigates the corpus's inherent structure from broad topics down to individual passages, deciding at each level which branches are worth exploring. Without task-specific training or a first-stage retriever, DecisionRAG outperforms dense retrieval with an 8B reranker by 13.8 R@1 points on MultiDoc2Dial and 17.4 Hit@1 points on Natural Questions. Across four benchmarks, including a corpus of 2.68 million Wikipedia paragraphs, retrieval takes just 0.7-1.8 seconds per query.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35865

Center-of-Mass Interpretation of Evolution Strategies

Akshat Gupta

原文摘要

Evolution strategies (ES) update a model by sampling a population of perturbed copies, scoring each one, and moving in the reward-weighted direction of the perturbations. This update is usually presented as an estimate of a smoothed gradient. We present a geometrical interpretation of this update instead. Treat each perturbed model as a particle and its reward as the particle's mass. Before scoring, every particle has the same mass and the population balances at its centroid. Once rewards are assigned, it balances at its reward-weighted center of mass instead. We show that the mean-subtracted ES update is exactly this displacement, scaled by a scalar factor that depends on the mean reward, for any finite population. The physical reading needs nonnegative rewards, which can always be arranged by adding a constant to every reward without changing the update. In the limit of a large population or under antithetic sampling, the centroid sits on the model itself, so ES has an even simpler geometric interpretation: from its current location, the model moves towards the reward-weighted center of mass of its own population. The same picture explains what subtracting the mean reward does: it changes the point from which the displacement is measured, from the model to the sampled centroid. Our contribution is an intuitive, geometric way to visualize an ES update, exact for any finite population.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35862

Learning Force-Reactive Humanoid Loco-Manipulation

Sihang Li, Xiaofeng Guo, Jinkun Cao, Charlie Cheng, Ruihan Yang, Chen Feng, Guanya Shi, Haozhi Qi

原文摘要

Many everyday tasks require controlling contact force as well as motion. On a humanoid, this force must often be coordinated across both hands and the whole body, and cannot be specified by kinematic trajectories alone. Therefore, we present FLORE, a framework for learning force-reactive humanoid loco-manipulation. We collect robot-free demonstrations using two force-sensing UMI-style handheld grippers for hand motion and contact wrenches, and wearable trackers for body motion. A force-reactive diffusion policy takes vision, proprioception, and measured wrenches as input, then predicts actions and per-hand force commands. A hybrid compliance whole-body controller with force tracking executes these commands while maintaining balance: an integral of the force error measured by real force/torque (F/T) sensors lets each hand track force accurately along the commanded direction and remain compliant along the others. In simulation, the controller tracks per-hand force commands of varied magnitude and direction, with little loss in whole-body motion accuracy. Across three contact-rich tasks on the robot, the force-reactive policy succeeds in 80% of rollouts, compared with 26.7% for a position-only policy trained on the same demonstrations and executed by the same controller. For more details, please visit our website: https://louis-leee.github.io/FLoRe/.

cs.RO · cs.AI · cs.LG · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35847

Patient-specific rubric-based evaluation of large language models across longitudinal cancer care

Wei-Wei Zhang, Pengkai Wang, Yan Li, Zhijie Sang, Guan-Qun Zhou, Jun-Yan Li, Shu-Han Zhou, Pei-Wen Liu 等 16 位作者

原文摘要

Large language models (LLMs) show promise in specialty medicine, yet existing evaluations largely focus on isolated clinical encounters rather than tracking how clinical responsibilities evolve across a longitudinal care pathway. Here we introduce NPC-RubricBench, a phase-aware benchmark for evaluating multistage clinical reasoning across the cancer care continuum, using nasopharyngeal carcinoma as a defined disease context. Curated from longitudinal records of 405 patients across two cancer centers, the benchmark comprises 941 patient-phase units across six sequential care phases and 17,688 patient-specific atomic criteria spanning five evaluation dimensions, with each assessment strictly restricted to decision-time clinical evidence. Evaluating 30 general-purpose and medical LLMs revealed that strong diagnostic performance does not carry over to downstream care. We evaluated 30 general-purpose and medical LLMs, showing that high diagnostic performance did not translate into improved downstream care. Instead, the dominant failure modes reversed across phases. Explicit decision errors dominated anatomical staging at 48.2%, whereas decision omissions dominated initial work-up and post-treatment follow-up at 33.4% and 30.4%, respectively. In the evaluated model set, medically adapted models showed higher omission rates than general-purpose models. Moreover, varying query granularity exposes a critical specification trade-off: broad open-ended requests degrade Decision Quality across all 30 models, while more detailed, checklist-like prompts raise Decision Quality but reduce Evidence Faithfulness and Safety Adherence. Furthermore, NPC-RubricBench demonstrates that static diagnostic benchmarks are insufficient to ensure consistent clinical reliability over time, highlighting the importance of phase-adaptive safeguards in multistage medical AI.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35832

Profiling a Frontier Agent with EBench: From Direct Control to Harness with Policy

Yifei Yao, Yude Zou, Guanbo Jiao, Xing Gao, Ning Gao, Yukai Wang, Jiantong Chen, Zihou Zhu 等 15 位作者

原文摘要

Frontier multimodal large language models (MLLMs) can control robots without robot-specific training, but how their capabilities compare and interact with post-trained vision-language-action (VLA) and world action model (WAM) policies across manipulation demands remains to be thoroughly evaluated. In this report, we evaluate GPT-6-Astra on EBench as the core of an agent that controls a robot through an agent harness under the same visual and proprioceptive observation protocol as post-trained policies. We study two agent configurations: direct control, in which the agent generates waypoint commands directly, and harness with policy, in which it can also invoke a post-trained VLA or WAM policy for action execution. Under direct control, the agent achieves competitive overall performance relative to post-trained policies. It leads on short-horizon tasks and exhibits the least performance variation across generalization dimensions, whereas it underperforms post-trained policies on long-horizon tasks, tabletop manipulation, and high-precision contact-rich tasks. In the harness with policy, invoking a post-trained VLA or WAM combines the complementary strengths of both components, raising overall task success to the level of the strongest compared post-trained policies while substantially reducing token cost. However, performance remains below the per-task upper bound of the standalone components due to suboptimal policy invocation, fixed-instruction execution without subgoals, and grasp disruption when the agent resumes control. Overall, our study characterizes the capability boundary of a frontier MLLM agent and suggests directions for improving future agent harness design. Project page: https://internrobotics.github.io/EBench-Astra-Tech-Report/

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35829

Reva: Real-Time Vulnerability Detection through Contextual Probing of Large Language Models

Amine Lbath, Massih-Reza Amini

原文摘要

A vulnerability costs more to fix the later it is discovered. As coding agents generate code faster than developers can review it, software needs a first line of defense screening each new function in real time. LLM agents have recently become capable of finding real-world vulnerabilities by working as a security expert would: they run analysis tools, explore the surrounding code, test hypotheses and weigh the evidence before forming their own judgement. This reasoning, however, spans many model calls, so that each verdict takes minutes of compute, far too long for real-time screening. Faster detectors, which fine-tune deep learning models or prompt an LLM for a direct verdict, are less accurate: they judge a function without the context an agent gathers, and an LLM's generated verdict is unreliable even when given some of it. We present REVA (REal-time Vulnerability Analysis), an AI vulnerability detector that brings the security context and code understanding components behind agentic detectors into a single forward pass of an LLM. For each new function, REVA gives the LLM a pre-computed threat model of its module, lightweight static analysis findings and call-graph information. REVA leverages a trained probe to read the LLM's internal representations of the new function in this context. On PrimeVul's held-out test set, REVA on GLM-5.3-Flash reaches 60.0% accuracy in about one second per function. This matches VulTriage (59.2%), the state-of-the-art agentic detector, run on the same LLM, while being over 250 times faster and less than a tenth as costly. On the same prompt, the probe is 14% to 17% more accurate than the LLM's own direct verdict. Across three open LLMs, REVA is at least as accurate as VulTriage, and about 10% more accurate on two of them. An LLM's internal representations thus encode much of what agentic detectors obtain through reasoning.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35804

Learning When to Commit: Schedule Distillation for Fast Diffusion Language Models

Aidar Myrzakhan, Zhiqiang Shen

原文摘要

Diffusion large language models (dLLMs) can generate multiple tokens in parallel, but often require many decoding rounds to complete a response. Efficient generation depends not only on which tokens are easy to predict, but also on how committing to them helps predict the remaining positions. A highly predictable token may provide little useful context, while revealing a less predictable token can help several other positions become predictable sooner. We propose dSpark, a new schedule distillation-based framework for learning when to commit tokens for faster diffusion language generation. To achieve this, we construct unmasking schedules that prioritize tokens whose reveal makes other positions easier to predict, reducing uncertainty earlier in decoding. We then distill these schedules into the model to enable faster parallel sampling, with a KL-divergence regularizer to help preserve generation quality. We extensively evaluate our approach across mathematical reasoning and code generation tasks. On GSM8K, our method achieves remarkable 10.12$\times$ and 5.12$\times$ speedups over the various baselines on LLaDA-8B-Instruct and Dream-7B-Instruct, respectively, while maintaining superior task performance. Our code is available at https://github.com/VILA-Lab/dSpark.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35802

Game theory of academic effort and hiring in the age of AI

Saptarshi Pal, Peter S. Park

原文摘要

Many academic disciplines (in particular, mathematics and the theoretical sciences) face difficult questions about how to adapt their practices to the rise of highly capable artificial intelligence (AI). Before AI, a well-written research paper with a strong theoretical result acted as a reliable signal that its authors understood their field in depth. Now that AI is widely accessible, such signals have become cheaper to produce. As a result, they no longer reliably sort academics by their level of understanding. This has direct consequences for academic hiring. The age of AI raises a question for each side of the academic job market. Should an early-career researcher invest in a deep understanding of their field, or instead use AI to build a longer resume with many papers? Should a recruiter favor applicants with fewer papers who pass an interview aimed at probing understanding, or insist on both publication volume and a pass? In this paper, we develop a game-theoretic model of this two-sided dilemma. We classify all pure-strategy equilibria that can arise in this game and use learning simulations to identify the behaviors that populations of applicants and recruiters may learn to adopt. Our analysis provides a framework for reasoning about how academic hiring can adapt to AI and for evaluating practices that preserve the value of deep understanding.

cs.AI · cs.CY · cs.GT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.21060

Divide et Calibra: Multiclass Local Calibration via Vector Quantization

Cesare Barbera, Lorenzo Perini, Giovanni De Toni, Andrea Passerini, Andrea Pugnana

原文摘要

Accurate and well-calibrated Machine Learning (ML) models are mandatory in high-stakes settings, yet effective multiclass calibration remains challenging: global approaches assume calibration errors are homogeneous across the latent space, while local methods often rely on representation-space dimensionality reduction, discarding latent directions relevant to miscalibration. To address these issues, we propose a compositional approach to multiclass calibration, where region-specific calibration maps are constructed from shared factors. We instantiate this idea via Vector Quantization (VQ), which induces a structured partition of the representation space, and an indexed parameterization of Dirichlet concentrations that enables parameter sharing across regions. Our approach learns heterogeneous calibration maps that generalize well even to sparse regions of the latent space. Experiments on benchmark datasets show significant improvements in local calibration while maintaining competitive global calibration and predictive performance.

cs.LG · cs.AI · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.15464

Where and What to Reward? Understanding Generalization Between Verifiable and Open-Ended Domains in Reinforcement Learning

Shangjian Yin, Yu Fu, Yue Dong, Zhouxing Shi

原文摘要

Reinforcement learning with verifiable rewards (RLVR) is widely used to improve the reasoning capability of language models, since model-generated answers can be easily verified by a rule-based verifier. In contrast, reinforcement learning from human feedback (RLHF) is mainly used to optimize open-ended conversation with a learned reward model, because such responses are not easy to verify. RLVR and RLHF are usually trained separately with their own domain data and training protocols. How gains transfer between these domains is unclear, partly because comparisons change both where a model is trained (the prompts) and what is rewarded (by a verifier or a reward model). We separate the two in a controlled study of RL on multiple base models that fixes the optimizer and the number of training prompts, and varies only the source domain of the prompts (math, multi-domain, chat, or mixtures) and the reward. We find that RLHF on open-ended prompts substantially improves conversational ability and also brings large gains in reasoning and coding, whereas RLVR improves reasoning but its gains in open-ended conversation plateau far below those of RLHF, suggesting that RL on open-ended prompts with a reward model can serve as an effective approach for generalizing across domains.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36015

Do Coding Agents Still Need a Debugger? Frontier-Model-Based Fault Localization at the Accuracy Ceiling

Christoph Daxerer, Johann Glock, Christian Macho, Rudolf Ramler, Martin Pinzger, Josef Pichler

原文摘要

Background: To localize a fault, a coding agent can reason from source code alone or use debugger assistance by running the program and stepping through it in an interactive debugger. While earlier agents struggled with static execution tracing and debugger operation, frontier LLMs have improved at both. Objective: We evaluate how accurately coding agents localize faults without tools across original and transformed programs, how much debugger assistance improves accuracy and at what cost, and how agents use it when optional. Methods: We seed 610 single-line faults into 144 LeetCodeDataset solutions and rewrite each faulty program with five recipes of behavior-preserving transformations. Agents based on Sol 6.1, Luna 6, and Qwen 3.8 localize each fault with no, optional, or encouraged debugger assistance. Results: Without tools, the agents localized 98.2 to 99.9% of faults in original and 96.7 to 99.9% in transformed programs, losing accuracy mainly where recipes restructured loops and conditions. Encouraged assistance removed 63% and 61% of Luna 6's and Qwen 3.8's remaining transformed errors (+2.1 and +1.3 percentage points) at 14.7 to 27.0 times the token use, while Sol 6.1 stayed at 99.9%. With optional assistance, Luna 6 and Qwen 3.8 still gained +1.5 and +1.3 points, though the agents used the interactive debugger in only 0.2 to 6.2% of runs. Conclusions: On short, precisely specified programs, current coding agents localize nearly all faults from source code alone, and debugger assistance removes most errors that remain. Given the choice, agents executed the program far more often than they stepped through it, yet kept most of the benefit.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35773

A Unified Arena for LLM Agents across Diverse Eurogame

Fengrui Zhang, Xiang Li, Ruomeng Ding, Jiayi Yuan, Yuchen Huang, Zhaoyang Han, Xiaoliang Wang, Daoyuan Chen 等 9 位作者

原文摘要

Interactive environments offer a practical way to evaluate large language model (LLM) agents, and competitive games extend this evaluation to decisions shaped by competing goals and other agents' choices. Yet existing evaluations confined to individual games or execution frameworks leave unclear which competitive advantages persist across settings. We introduce DECE (Diverse Eurogame Competitive Environments), a unified arena spanning ten Eurogames with shared interfaces and evaluation protocols. These games combine lasting strategic commitments, competition over shared resources, and multiple routes to victory. Our primary study evaluates 12 model-harness configurations, spanning nine models and four execution harnesses, in 480 three-player matches across ten games. The main and supplementary studies comprise 1,032 completed matches in total. These comparisons reveal broad cross-game ranking agreement alongside game-specific strengths. Matched studies show that the same model can perform differently across execution harnesses, adding another source of variation to these profiles. These performance advantages do not consistently translate into better token or cost efficiency, making resource use an additional consideration when comparing configurations. Together, the findings support evaluating complete agent configurations by both their competitive performance across games and the resources needed to achieve it.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.16051

Loop the Loopies!

Zitian Gao, Yilong Chen, Yihao Xiao, Xinyu Yang, Ran Tao, Joey Zhou, Bryan Dai

原文摘要

We present Loopie, the most powerful open-source looped Transformer to date. The Loopie series consists of two Mixture-of-Experts (MoE) models: a 20B-parameter model with 2B active parameters and a 6B parameter model with 0.6B active parameters. Looped Transformers have long faced a challenge: given an N-fold pre-training compute, increasing the parameter count by a factor of N usually outperforms looping N times. Loopie addresses this challenge. Extensive ablation studies, including comparisons with a vanilla 30B-A3B model, show that Loopie substantially outperforms vanilla Transformer baselines trained with the same compute budget. With a novel post-training method, Loopie develops strong reasoning abilities and achieves frontier-level reasoning performance.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35767

Free to Look, Free to Reason: Simple LLM Harnesses Outdiagnose Hand-Crafted Root Cause Analysis Agents

Tingzhu Bi, Xun Zhang, Jinglin Li, Ping Wang, Meng Ma

原文摘要

Root cause analysis (RCA) of microservice failures has attracted many LLM agents whose investigation is hand-crafted, through standard operating procedures, fixed stages and role agents. Each is evaluated on its own data against few baselines, so it is unknown whether this design beats letting a capable model investigate on its own. We compare three simple harnesses that prescribe none of the model's calls (one call over an evidence package, a SQL agent and the Codex coding agent) with five published LLM RCA agents and with statistical and causal methods on RCAtlas, 90 validated cases from eight public datasets, across six models and three reasoning efforts. The simple harnesses are the most accurate (PR@1 65-77% on three mid-tier models), ahead of the published agents (16-53%) and the non-LLM methods (6-39%), on every model on which both families were run. The published agents fix from a tenth to all of their model calls in the program, and a case study shows how these prescriptions skip the decisive evidence. A stronger model mainly improves reliability, a multi-turn harness mainly improves aptitude, and more reasoning effort changes accuracy by a few points at most while multiplying the time by up to seven. Among runs more accurate than the best non-LLM method, every Pareto-optimal run in cost or time uses a simple harness.

cs.AI · cs.DC · cs.SE

查看论文
arXiv ↗PDF ↗