跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

arXiv 最近完成扫描：2026-11-08 22:53 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 23:20 — 2026-11-08 23:20（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-08 22:53最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

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

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

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 22:48（北京时间）
新论文 · v1arXiv:2610.40256

When Requirements Interact: Scaling Long-Horizon Coding via Interdependent Specifications

Yishuo Cai, Minzheng Wang, Liang Zhao, Linghao Zhang, Lei Li, Shicheng Li, Xu Sun, Fuli Luo

原文摘要

To succeed in real-world long-horizon software development, coding agents must satisfy multi-dimensional task specifications, such as interface compatibility and error handling, and do so without breaking existing dependencies. However, current works lack specification in both quantity and diversity, often emphasizing primary goals while ignoring complex constraints. Synthesizing tasks to bridge this gap presents two challenges: naively adding specifications risks reducing tasks to trivial checklists rather than compelling joint reasoning, and verifying these subtle interactions risks overlooking hidden flaws or rejecting valid alternatives. To address these challenges, we introduce CodeSpecWeave, a framework for synthesizing tasks with rich, interdependent specifications. Grounded in real developer seeds, a synthesis agent iteratively develops both coupled task requirements and executable tests, while a review agent audits solution trajectories from multiple models to guarantee test reliability. Using this pipeline, we construct 4,670 training tasks across 2,865 repositories. Applying Reinforcement learning on these tasks significantly improves performance over the base model on DeepSWE-v1.1, largely outperforming existing baselines. Furthermore, we curate CodeSpecWeave-Bench, a rigorous benchmark comprising 100 tasks and 1,044 specifications, which clearly separates frontier models and reveals significant headroom in handling interdependent engineering constraints.

cs.SE · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40254

Statistical Analysis of Synthetic Data with Verification: A Linear Regression Framework

Heejune Sheen, Harrison H. Zhou

原文摘要

Synthetic data are widely used for training modern AI systems. However, their statistical understanding remains limited. It is well recognized in statistics that repeated self-training on synthetic data can amplify errors inherited from pre-trained models, leading to model collapse. Verification plays a crucial role in selecting high-quality synthetic data to help prevent model collapse and improve model performance. We study verified self-training in a linear regression framework, where a pre-trained estimator generates synthetic data with injected generation noise and a verifier selects samples according to a verification threshold. Post-training on the accepted samples updates either all coordinates (full fine-tuning) or only an active subset (partial fine-tuning). Our analysis reveals three potentially counterintuitive effects. We establish that tighter verification does not always lead to lower prediction risk. We also find that a suitable level of injected generation noise can reduce prediction risk, while excessive noise can increase it. Moreover, full and partial fine-tuning can respond differently to the same verification rule, since pre-training error in the frozen coordinates affects both sample selection and post-training risk. We analyze these effects by deriving finite sample risk bounds for four separate regimes determined by the relative scales of the verification threshold, generation noise, and pre-training error. The bounds precisely characterize how verification affects prediction risk across these regimes. In particular, we quantify how the generation noise, the effective accepted sample size, and the covariance of the accepted covariates affect prediction risk. The analysis extends to iterative verified full fine-tuning, where sufficiently tight verification reduces the initial error contribution at a geometric rate.

stat.ML · cs.LG · math.ST

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40253

Confidence-Aware Speed-over-Ground Estimation from Doppler Spectra via Reconstruction-Based Representation Learning

Malte Stelzer, Marvin Sach, Timo Bartels, Dinu Mihailescu-Stoica, Sören Kohnert, Florian Poprawa, Marc Zeller, Tim Fingscheidt

原文摘要

Reliable speed-over-ground estimation from ground-facing Doppler spectra is essential for mobile platforms such as railway systems. Classical signal-processing approaches can provide accurate estimates under favorable conditions, but often degrade in challenging conditions. We propose confidence-aware speed-over-ground estimation trained on rail-domain data that estimates speed over ground and frame-level confidence from Doppler spectra with several novel contributions: First, we transfer the idea of exploiting a reconstruction task by an autoencoder for performance estimation from previous work to Doppler RaDAR. Second, we append a speed-over-ground estimation head operating on the autoencoder's latent space features. Third, we omit the reconstruction decoder during inference but add a low-cost dedicated confidence head for frame-wise error-bound estimation. Fourth, we reveal how noise augmentation training can provide high robustness to the method. Experiments show that our approach improves speed estimation accuracy over classical baselines while providing informative confidence estimates that indicate the reliability of individual predictions, even under adverse signal conditions.

eess.SP · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40252

Conformal Annotation with Randomized Expert Review: Application to Online Cell-Type Labeling

Xuhe Zhang, Zhi Huang, Ying Jin

原文摘要

Artificial intelligence (AI) models can accelerate cell-type annotation in digital pathology, but safely scaling their use requires determining, with error control, which model-generated labels can be accepted without expert review. This is challenging in evolving workflows because cell morphology and type composition may change across tissue regions and slides, making one-time calibration unreliable. We propose Conformal Annotation with Randomized Expert review under Distribution shift (CARED), a distribution-free framework that leverages randomized expert audit to achieve long-run error control for AI-assisted annotation under distribution shift. For each incoming batch, CARED uniformly selects a subset of cases for expert review and uses the acquired labels to calibrate later decisions. Among unreviewed cases, CARED determines a subset of them to safely skip expert labeling, while suggesting candidate labels for the others for downstream resolution. We prove that this workflow provides long-run control of cumulative error over both the full stream and the cells outside of the audit sample, without stationarity or exchangeability assumptions. We further enhance the framework by introducing class-conditional guarantees to ensure error control within important but rare cell types, together with a utility module to target more automatic resolutions, smaller candidate sets, and greater biological coherence, without compromising validity. Experiments on pancreas, lung, and ovary annotation streams, together with a stream constructed from real expert annotations, show that CARED controls the cumulative errors while a substantial fraction of cells (up to 70%) bypass expert review.

stat.ME · cs.LG · stat.AP · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40250

Distributional Reward Calibration and Budget-Neutral Credit Assignment for Multimodal RLVR

Lang Chen, Zongxin Xu, Borui Wang, Anran Liu, Shitong Chen

原文摘要

We revisit advantage estimation in Group Relative Policy Optimization (GRPO) and observe that any token-level advantage admits a two-stage factorization: a \emph{sample-level baselining} step that converts scalar verifier rewards into a comparable sequence-level signal, and a \emph{token-level credit assignment} step that distributes that signal over the trajectory. Existing estimators typically address only one of these stages: affine baselines preserve the shape of each task's reward law, so heavy tails and binary cliffs propagate into the gradient, while token-level credit rules tie the size of each token's update to raw confidence scales and need not conserve the total credit issued by the verifier. We propose \textbf{TACE} (Two-stage Advantage and Credit Estimation), a two-stage estimator that addresses both stages. At stage~(S1), we replace linear standardization with a one-dimensional optimal-transport map to a standard normal, which gives a common population reward law across tasks and caps finite-sample outliers deterministically. At stage~(S2), we rank-calibrate a stop-gradient evidence contrast within each trajectory and renormalize the clipped token weights to have mean one, so credit is redistributed across tokens while its total mass and sign are conserved. We prove population-level inter-task moment equity, a deterministic tail bound, and mass-conservation, boundedness, and sign-anchoring properties that affine baselines and unnormalized token weights do not satisfy. On a multimodal reasoning suite, TACE obtains the strongest results on a majority of the benchmarks but does not dominate every setting.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40249

Reaction precedents extend retrosynthetic prediction beyond training coverage

Jiaxing Sun, Xuli Shen, Jiang Wu, Ruiyi Ding, Ruikang Zhang, Xiao An, Xibao Li, Yubin Wang 等 20 位作者

原文摘要

Reaction precedents guide retrosynthesis, but how far they can compensate for gaps in task-specific training coverage remains unclear. Using 2.71 million reactions, we restricted training and retrieval coverage by transformation or time, then expanded only the retrieval corpus with model parameters fixed. For transformations excluded from training, mean Top-1 accuracy increased from 13.0% to 58.0% on a historical test set and from 4.9% to 23.1% on a temporally held-out test set. For temporal coverage gaps, retrieval expansion enabled a model trained on records before 2017 to match or exceed a non-retrieval model trained on records before 2025 on both test sets. Without task-specific fine-tuning, precedents improved all 14 representative general-purpose models on both test sets and USPTO-50K; the strongest with precedents surpassed all eight representative specialized models. These findings show that inference-time reaction precedents can extend retrosynthetic prediction beyond task-specific training coverage without parameter updates.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40248

LLM-guided Planar Loco-Manipulation for Quadruped Robots

Georges Jetti, Michael Khayyat, Jean-Pierre Sleiman, Stefano Arrigoni, Francesco Braghin

原文摘要

Robotic navigation typically assumes a collision-free route to the goal exists; in cluttered environments with movable obstacles, however, reaching the goal may require physical interaction. Classical solutions encode these behaviors through geometric rules and task-specific logic, while learning-based approaches often constrain the decision space to low-dimensional motion commands or predefined action sets. We instead consider a broader decision space, jointly selecting the skill, relevant object, and geometric target. Our language-conditioned task planner, fine-tuned with LoRA on synthetic data, maps natural-language tasks and a structured scene representation to variable-length sequences of parameterized actions, executed by low-level reinforcement-learning policies. The planner learns the geometric relations underlying interactive navigation and outperforms a classical planner and a prompted frontier model on interactive navigation tasks. Comparisons with models trained from scratch indicate that composition does not require pretraining when the representation is structured, whereas pretraining yields more reliable geometric targets. At the low level, we introduce an end-to-end whole-body planar pushing policy that achieves a 93.3% success rate in simulation, versus 83.5% for a hierarchical baseline, while reducing completion time by more than 60%. On hardware, the hierarchy yields the correct skill composition in 44/45 trials and end-to-end success in 34/45. Project website: https://anonymousprojects-dev.github.io/LLM-guided-LocoManipulation-Quadrupeds/

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.02479

PRISM: Pushing the Frontier of Deep Think via Process Reward Model-Guided Inference

Rituraj Sharma, Weiyuan Chen, Noah Provenzano, Tu Vu

原文摘要

DEEPTHINK methods improve reasoning by generating, refining, and aggregating populations of candidate solutions, which enables strong performance on complex mathematical and scientific tasks. However, existing frameworks can still suffer from unreliable correctness signals during inference, which creates a population- enhancement bottleneck where deeper deliberation amplifies errors, suppresses correct minority solutions, and yields weak returns to additional compute. In this paper, we introduce a functional decomposition of DEEPTHINK systems and propose PRISM, a Process Reward Model (PRM)-guided inference algorithm that uses step-level verification to guide resampling, proposal acceptance, and solution aggregation. During refinement, PRISM uses PRM scores to guide population resampling and stochastic local refinement, which concentrates computation on higher-quality reasoning while preserving diversity. When paired with PRM- score-vote, a PRM-guided aggregation method, PRISM is competitive with or outperforms existing DEEPTHINK methods, reaching 90.0%, 75.4%, and 71.4% with gpt-oss-20b on AIME25, HMMT25, and GPQA Diamond, respectively, while exceeding gpt-oss-120b. Additionally, our analysis shows that PRISM produces consistent net-directional correction during refinement and maintains competitive accuracy when the initial population contains few correct candidates.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40246

EnvOS: Auditing Computer-Use Agents When the World Moves On : Phenomenon-Based Task Construction, Certification, and Evidence-Based Evaluation

Ankush Kadu, Athira Gopal, Niharika Singh, Arpit Jain, Aswanth Krishnan

原文摘要

Computer-use agents built on large language models (LLMs) work in software that can change while they act: an appointment moves, a policy is revised, a record is updated. Testing agents under such changes is harder than it looks. When an agent fails, the cause may be the agent, but it may also be a change that did not fire as intended, an update the agent never received, or a grader that scored the episode wrongly. We introduce EnvOS, a framework for building and certifying environments that change mid-task. Before any agent runs, EnvOS checks that each change fires correctly, that the task remains solvable, and that the grader separates correct from incorrect behavior; after each run, separate code re-checks the verdict from archived evidence. We apply it to stale information, where a value the agent has already seen changes before the agent acts on it. In clinic booking, Claude Opus 5 succeeds on 0/16 tasks when nothing extra is shown, 2/16 when reminded to re-check the source, and 15/16 when the updated value is shown; the gain over the reminder holds after correcting for all tests (p = 0.00293). In insurance-claim approval, Opus 5 re-checks on its own and succeeds on 10/10, whereas Claude Sonnet 5 rises from 1/10 to 9/10 when the current policy is shown again, a gain significant in its pre-registered test but not after correcting for all tests. Whether an agent caught a change thus varied with the model and the interface. We also stress-test the grading itself: on corrupted episodes designed blind from the rules, the EnvOS pipeline accepted none of 26 as clean, and on an externally generated set it caught 25 of 39, against 4 for simple log checks. Because every EnvOS environment is generated from a seed and graded by an audited automatic verifier, the same environments are natural candidates for training agents with reinforcement learning from verifiable rewards.

cs.AI · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40241

Judged in Company: In-Context Batching Makes LLM Verdicts Depend on Other Items

Peng Xie, Amr Alanwar

原文摘要

To save cost, practitioners often ask a language model to grade many independent items in one prompt. This assumes that verdicts are separable: that the verdict on an item does not depend on the other items in the prompt or on its position among them. Across three judgement tasks (harm in social-media comments, short-answer grading and review star ratings) and five open-weight models with 4-9B parameters, assigning the same 2,000 items to different random batches of 25 changes 11-22% of decisions on harm and grading, 6.5-13.3 points more than renaming the item keys or rewording the instruction, while AUROC against human labels differs from single-item grading only by -0.033 to +0.010; for four models with 14-32B parameters, 6-15% of decisions change, 4.2-9.1 points more. We show that flip rates decompose exactly into components of order, slot and membership, and that under a threshold model they grow with the square root of the variance that the context contributes, so that effects that are small for scores are large for decisions. Most of the latent dissimilarity between partitions comes from the order of the neighbours and the slot. The main effect of which items share the prompt, the part that voting over permutations of a batch cannot remove, accounts for 0.11-0.22 of it, and majority votes over nine permutations still leave 52-60% of the flips. Batched verdicts also differ systematically from single-item verdicts: even the majority of fifteen random batches disagrees with them on 8.4-17.8% of decisions. Editing a single generation shows that both the model's own earlier verdicts and the neighbours' texts carry the effect. On the easy task, star ratings, only 2.9-3.9% of decisions change. We recommend grading ambiguous items one per prompt, recovering most of the cost with a cached prefix, and reporting agreement with single-item grading whenever items are batched.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40239

Engineering process plants as code in the age of agentic AI

Artur M. Schweidtmann, Davy Demeyer

原文摘要

Agentic artificial intelligence (AI) could one day shorten process plant engineering from years to weeks. Today, however, plant information is scattered across documents and tools and must be carried between them by hand, so an AI agent placed into current workflows inherits the same silos. In this Comment, we argue for Plant-as-Code: defining the engineering of a plant as a version-controlled collection of machine-readable files that follow, where possible, existing standards such as DEXPI and IFC. On this foundation, Design-Ops extends DevOps principles to plant engineering, linking every engineering item to the information it derives from and replacing manual checking with automated tests. Agents can then coordinate routine work across disciplines while deterministic tools perform the calculations. Verification sets the pace: agents propose, tools check, and engineers review and authorize every change. We outline the risks of this shift and the research, industry and policy actions it requires.

cs.CE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40238

ScienceJudge: Pattern Perturbation Augmentation for Sentence-Level Scientific Claim Verification

Chuhai Cai, Xin Chen, Min Yang, Feng Jiang

原文摘要

Sentence-level scientific claim verification determines whether each sentence in an AI-generated scientific paragraph is supported by a given multimodal evidence bundle. Fine-grained reporting errors often preserve fluent and plausible statements while introducing subtle evidence-claim deviations, making them difficult to detect under sparse and imbalanced supervision. We propose Pattern Perturbation Augmentation (PPA), which models reporting errors as label-specific faithfulness breaking transformations and induces reusable error patterns from labeled examples. PPA applies these patterns to supported claims to construct controlled hard negatives and expands their coverage through pattern-level, operation-level, and cross-domain augmentation. Based on these augmented views, we develop ScienceJudge, which integrates PPA-trained vision-language predictors and instruction-guided LLM predictors through class-weighted ensemble inference. On the local development set, ScienceJudge improves the average score from 0.8124 to 0.8692, achieving a Macro-F1 of 0.8466 and a Paragraph Exact Match score of 0.8919. Our submitted system ranks first on the official NLPCC 2026 Task 10 Track 1 leaderboard with a final score of 0.6890.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.15315

Evaluation Metrics for Safe Reinforcement Learning

Lindsay Spoor, Aske Plaat, Thomas Moerland

原文摘要

Safe reinforcement learning (RL) is commonly formalized as a Constrained Markov Decision Process (CMDP), in which an agent maximizes expected reward while keeping its expected cumulative cost below a specified safety bound. Existing safe RL benchmarks predominantly report whether an algorithm is safe on average, following this expectation-based guarantee. We argue that this convention is insufficient to reliably characterize an algorithm's true safety: it fails to capture how often and how severely the safety bound is violated, whether this holds consistently across tasks and safety bounds, and whether training-time behavior is representative of behavior of the final converged policy. Therefore, we introduce (i) evaluation metrics for safe RL that address each of these concerns and in addition allow for aggregation across tasks and safety bounds. We furthermore define (ii) a safety tier system to systematically categorize and compare algorithms in terms of safety and reliability at both training and for a final policy. Using this framework, we provide (iii) an empirical safety evaluation across multiple safety navigation tasks. Our results show that aggregate metrics, distributional reporting, and task- and safety bound-specific results each reveal information the other metrics cannot. We therefore recommend reporting all three jointly, rather than compressing this information into a single value, as is common practice. We provide SafeRLEval, an open-source evaluation suite to support the reliable characterization of safety in future safe RL research.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.34583

The German Tank Problem & Navigating by Scent

Kordel Kade France

原文摘要

A robot searching for the source of an odor must eventually answer a notably hard question: have I arrived? Near the source, concentration gradients homogenize, turbulence corrupts the signal, and a small robot often lacks the positional accuracy to map the plume. Here, we describe a lightweight remedy inspired by a World War II statistics conundrum: the German tank problem. To approximate German armament production, Allied analysts developed an estimator based on serial numbers from captured tanks. Analogously, we use the same procedure over sampled chemical sensor readings from a robot to create estimates for the peak concentration of an odor plume, and therefore the odor's source. Treating each sensor reading as an observation, our unbiased estimator needs only a running maximum and a sample counter. A confidence bound turns both numbers into a principled rule that the robot or UAV can use to determine whether it should keep searching for the odor source. We derive the estimator and its bound, demonstrate its sample efficiency, and examine its robustness even when its assumptions fail. Finally, we summarize the estimator's role as the termination criterion for olfactory navigation.

cs.RO · cs.ET · math.PR · math.ST

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.24832

Difference-Making without Making a Difference

Sander Beckers

原文摘要

Over a series of seven papers, Andreas & Günther have introduced seven definitions of actual causation and have classified them as belonging to three different, competing, types of accounts: factual difference-making, counterfactual difference-making, and regularity-based. I show that their most recent -- factual difference-making -- definition instantiates all three types, thereby proving that these are distinctions without a difference. I further compare their novel account to the other six accounts on several crucial examples, revealing that this undermines all seven of their accounts.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.19345

When Is Smaller Greener? Right-Sizing Language Models for Agentic AI

Sajid Siraj, Maria Barbati

原文摘要

AI agents use a large language model (LLM) to plan and act over many steps. Which model should an agent use, so that its tasks are completed reliably with the least energy, cost and time? We treat this as a multi-criteria decision problem in which comparisons per call can mislead: a task succeeds only if all its steps succeed, and failed attempts still use resources. We therefore compare models on resources per successfully completed task. We derive crossover task lengths at which two models exchange their efficiency ranking, determined by their per-step reliability and resource use. Each objective has its own crossover. Below the shortest crossover the less reliable model dominates, above the longest the more reliable one dominates, and in between both are Pareto-efficient and preferences decide. This supports a two-stage framework: a preference-free dominance screen, followed by a multi-criteria ranking of the efficient models, subject to reliability and feasibility constraints. We also give conditions under which this structure holds when reliability and resource use change during a task. In a pilot with 15 open-weight models on two synthetic agent tasks, with measured GPU energy, the predicted crossover fell within the observed range for 72 of the 88 observed crossovers. At 20 steps, a 3-billion-parameter model used a tenth of the energy of a 27-billion one per completed task; at 100 steps, a 1.7-billion model used almost four times as much as an 8-billion one. Smaller is greener only up to a task length that can be predicted.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40234

Unraveling the Efficacy of Neuron Coverage Criteria on Testing Large Language Models

Xiaoning Ren, Jiayang Song, Chongyang Liu, Jie Li, Lei Ma, Yinxing Xue

原文摘要

Neuron coverage criteria aim to assess test suite quality and guide test input generation, but their effectiveness for Transformer-based language models remains unclear. We evaluate six criteria, including four established and two recent criteria, across encoder-only, decoder-only, and encoder-decoder models. Our evaluation examines error-revealing capability, distribution diversity, sample fairness (category diversity), and guidance for test input generation. The results reveal uneven effectiveness. Erroneous samples provide only 0.32% additional coverage over noise samples, indicating limited sensitivity to adversarial errors. By contrast, coverage criteria effectively assess distribution diversity and sample fairness in 26 and 30 of 33 configurations, respectively. Incorporating neuron-wise coverage guidance into test input generation increases adversarial sample production by only 4.56%. These findings suggest that existing coverage criteria can serve as an antidote for assessing diversity but remain largely a placebo for revealing adversarial errors, particularly when used individually. Their practical value therefore depends on whether these limited benefits justify the computational overhead of testing large Transformer-based models. Our study highlights the need for more robust and efficient coverage criteria tailored to these models, with stronger error-revealing capability and greater value for test generation.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40233

Mobilizing the Archive: Bitext Extraction at Scale from Archival Documents for Extremely Low-resource Languages

Chutong Meng, Alec J. Bateman, Antonios Anastasopoulos

原文摘要

While mining parallel sentences from web pages has proven effective for low-resource machine translation, the majority of the world's languages have little to no web presence. What they do have, though, are resources that are the result of centuries of efforts by linguists, such as grammars, dictionaries, and other documentation materials. We propose extracting translation examples from such linguistic resources, which offer parallel data for languages under-represented online and could potentially scale to thousands more languages. We develop a pipeline to achieve this, leveraging an Optical Character Recognition (OCR) model as well as a vision language model (VLM), to ensure identified content to be aligned with visual layout information. We demonstrate the utility of the extracted bitexts for bootstrapping translation systems across 20 languages, both by training machine translation models and by applying in-context learning for large language models. For in-context learning, we observe improvements of +15.78 and +6.94 chrF2++ over zero-shot translation for into low- and high-resource languages, respectively.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.13803

EvoGround: Self-Evolving Video Agents for Video Temporal Grounding

Minjoon Jung, Byoung-Tak Zhang, Lorenzo Torresani

原文摘要

Video temporal grounding (VTG) takes an untrimmed video and a natural-language query as input and localizes the temporal moment that best matches the query. Existing methods rely on large, task-specific datasets requiring costly manual annotation. We introduce EvoGround, a framework of two coupled self-evolving agents, a proposer and a solver, that learn temporal grounding from raw videos without any task-specific annotations. The proposer generates query--moment pairs from raw videos, while the solver learns to ground them and feeds back signals that improve the proposer in return. Through this self-reinforcing reinforcement-learning loop, the two agents are initialized from the same backbone and mutually improve across iterations. Trained on 2.5K unlabeled videos, EvoGround matches or surpasses most fully supervised models across five VTG benchmarks, while emerging as a state-of-the-art fine-grained video captioner. We publicly release all resources at https://minjoong507.github.io/projects/EvoGround/.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40227

EpiAgent: Epistemic Self-Play for LLM Agents

Xuanfa Jin, Xinyu Cui, Zhijian Ma, Xue Yan, Jian Zhao, Haifeng Zhang, Jun Wang

原文摘要

Epistemic game theory explains an agent's strategic behavior via the beliefs it holds about others and how these beliefs are updated as the interactions unfold. Modern LLM-based agents, however, often lack an explicit mechanism for learning and updating such beliefs to guide decisions under incomplete information. To bridge this gap, we propose EpiAgent, a framework that equips LLM-based agents with an explicit, learnable epistemic layer, which maintains beliefs over others' private information and combines these beliefs with the agent's available information into an epistemic state for action selection. Concretely, the agent's policy is decomposed into two coupled stages: Epistemic Update, which updates these beliefs from interaction histories, and Action Planning, which selects actions conditioned on the updated epistemic state. By formulating their dependency as a bi-level optimization problem, we introduce Epistemic Self-Play, an algorithm that alternately optimizes the two stages through self-play, utilizing an intrinsic prediction reward to evaluate how well inferred beliefs predict subsequent observations. Empirical results across both mixed and competitive scenarios show that EpiAgent consistently outperforms prompting-based and RL-based baselines. Further analyses reveal the benefits of dedicated epistemic training, improvements in belief inference accuracy, and the contribution of learned beliefs to action planning. These results demonstrate the value of an explicit, learnable epistemic layer for effective multi-agent interactions.

cs.AI · cs.CL · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40224

"It Feels Weird to Just Rely on AI": How Experienced Healthcare Professionals Work With Decision Support Systems in Clinical Practice

Simon W. S. Fischer, Hanna Schraffenberger, Miranda L. van Hooff, Casper Reijnen, Serge Thill, Pim Haselager

原文摘要

Decision support systems (DSS) assist with clinical decision-making. Little is known, however, about the decision-making process with DSS in clinical practice and the extent to which clinicians consider or rely on the predictions. Studies on human-AI decision-making usually focus on laypeople, simplified decision tasks, or one-shot interactions with prototypes that are not integrated into existing workflows. To gain insights from real-world practice, we conducted an online survey (n=12) and semi-structured interviews (n=10) with clinicians from two different medical cohorts each working with a DSS. Findings show, amongst other things, that the interaction with DSS changes as experience increases, the predictions become more important in complex cases, that decisions are discussed with colleagues, and that workflow integration affects decision-making. Our findings on human, technical, contextual, and organisational factors contribute to a socio-technical perspective on DSS reliance behaviour. We conclude by discussing the implications of our findings for the design of DSS.

cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.34928

Beyond Compilation Feedback: Refining Vulnerability Checkers with Program-Analysis Evidence

Chengzhi Yi, Shenao Wang, Yanjie Zhao, Xiao Cheng, Haoyu Wang

原文摘要

Recent work shows that LLMs can synthesize static-analysis checkers from security patches, but a compilable checker is not necessarily a correct one. A patch reveals what changed, not why the change is safe, so generated checkers often match only the surface edit and miss the deeper semantic condition. Existing refinement loops feed back compilation errors and validation reports, yet these signals describe symptoms without explaining what the checker misunderstands about the code. We observe that the analysis framework itself already computes the information needed to close this gap. Control-flow graphs, symbolic values, memory regions and checker callbacks are available inside the analyzer but unused by current refinement strategies. SemWeaver is a plug-in refinement layer that extracts patch-relevant analyzer evidence and assembles it with source context and validation feedback into a structured, provenance-labelled bundle. An iterative editing loop refines the checker on both the vulnerable and fixed revisions, guarded by a retention gate that accepts warning recovery or false-positive reduction while preventing over-pruning. We evaluate SemWeaver on 39 KNighter-derived CSA checkers from Linux kernel fixes. With analyzer evidence, refinement reaches 23 warning-positive vulnerable revisions (vs. 15 for KNighter's loop) and raises version-level $F_1$ from 0.448 to 0.575. An ablation removing internal evidence recovers fewer silent cases and produces different checker edits, indicating that the two evidence configurations address complementary recognition gaps. Additional experiments cover three editor models on a 12-subject subset, a CodeQL query refinement, and controlled source-form variations. A qualitative follow-up on all 11 non-tied comparisons traces each warning-count change to a specific checker repair, such as recognizing a lowered callback or unwrapping an expression cast.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.13112

AdaGrad-Diff: a Corrected Version of the Adaptive Gradient Algorithm for Composite Optimization

Matia Bojovic, Saverio Salzo, Massimiliano Pontil

原文摘要

Vanilla gradient methods are often highly sensitive to the choice of stepsize, which typically requires manual tuning. Adaptive methods alleviate this issue, with AdaGrad being a prominent example. In this work, we first show that, in composite convex optimization, AdaGrad may fail to exploit the Hölder-smoothness of the differentiable term, as its stepsizes may decrease too rapidly, leading to convergence rates arbitrarily close to the nonsmooth $\mathcal O(n^{-1/2})$ rate. Motivated by this limitation, we study AdaGrad-Diff, a block-wise extension of the UniSgd method considered by \cite{rodomanov2024universality}, which accumulates successive gradient differences rather than gradients themselves. In the deterministic Lipschitz-smooth setting, we prove summability of squared gradient differences without assuming bounded iterates, yielding weak convergence to a minimizer in Hilbert spaces. Moreover, we show that, under $ν$-Hölder-smoothness, stepsizes decay no faster than $n^{-(1-ν)/2}$, thereby avoiding AdaGrad's failure mechanism and recovering the standard $\mathcal O(n^{-(1+ν)/2})$ rate. The same approach recovers known stochastic convergence rates under a unified condition covering bounded variance and interpolation. Numerical experiments demonstrate that the proposed method is more robust than AdaGrad in several practically relevant settings.

stat.ML · cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40214

DYNAS: A Dynamic Network Penetration Testing Framework Using Deep Hierarchical Reinforcement Learning

Md. Rakibul Hassan, Majedul Islam, Md. Ashraful Alam, Muhammad Iqbal Hossain, Swakkhar Shatabda

原文摘要

As network scale and uncertainty complicate automated penetration testing, reinforcement learning (RL) environments must support controlled evaluation under defensive and non-stationary conditions. We present DYNAS (Dynamic Network Attack Simulator), which combines parameterized large-scale scenario generation with stateful intrusion detection responses, explicit scan false-positive and false-negative noise, temporary service unavailability, and duration-based action timeouts. We further introduce Pen-DHRL, a recurrent manager--worker policy that selects persistent subgoals using IDS-conditioned global context. We compare Pen-DHRL with GNN, Invariant, and Attention baselines across four scenario variants and multiple training regimes. Under IDS-disabled training followed by IDS-enabled evaluation, Pen-DHRL obtains approximately 64\% and 24\% higher reward per step on Bridge and Dynamic, respectively, and approximately 26\% and 30\% more captured hosts on VarA and VarB than the next-best baseline. With all defensive dynamics active from the beginning of training, Pen-DHRL achieves positive mean episode returns in all four scenarios, whereas the flat baselines produce negative mean returns in all 12 architecture--scenario combinations; staged curriculum training produces positive mean returns across all 16 evaluated combinations.

cs.CR · cs.LG · cs.NI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.00234

Blockspace Under Pressure: An Analysis of Spam MEV on High-Throughput Blockchains

Wenhao Wang, Aditya Saraf, Lioba Heimbach, Kushal Babel, Fan Zhang

原文摘要

On high-throughput, low-fee blockchains, a qualitatively new form of maximal extractable value (MEV), spam MEV, has emerged: searchers submit large volumes of speculative transactions, whose profitability is resolved only at execution time. On major rollups, it can consume more than half of block gas, even though only a small fraction of probes ultimately results in a trade. Despite growing awareness of this phenomenon, there is no principled framework for understanding how blockchain design parameters shape its prevalence and impact. We develop such a framework, modeling spam transactions competing for on-chain opportunities under a competitive equilibrium that drives their profits to zero, and deriving equilibrium spam volumes as a function of block capacity, minimum gas price, and the transaction fee mechanism. Empirical evidence from Base and Arbitrum is consistent with several predictions of the model: spam grew sharply as block capacity was scaled up and fell when minimum gas prices were introduced. Our analysis yields three main insights. First, spam is always costly: when block capacity is scarce, it displaces users and drives up gas prices; as block capacity grows, it increasingly consumes execution resources, raising network externality, i.e., the cost of provisioning and processing blocks. We show that spam takes an increasing share of each additional unit of block capacity, so capping it before all users are included creates a favorable trade-off: forgoing a small amount of user welfare eliminates disproportionate spam and externality. Second, we extend the analysis to approximate priority fee ordering and show that it can reduce spam by making earlier block positions more expensive, as spammers pay more to reach early block positions. Third, as user demand grows and blockspace is scaled accordingly, spam's share of block capacity plateaus rather than growing indefinitely.

cs.GT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40212

Benchmarking color judgment in multimodal LLMs with CIE-computable ground truth

Shuwei Yue, Kaida Xiao, Zhihua Wang, Qiao Chen

原文摘要

Multimodal large language models (MLLMs) are now used as zero-shot judges of image quality, but their color judgments are rarely tested with colorimetric ground truth. We present a five-task benchmark based on the CIE colorimetric framework: AWB pair judgment, skin-tone bias direction, CCT estimation, CIE Delta E 2000 pair ordering, and color naming under changing illuminants. We test eight MLLM endpoints, including four Qwen3-VL variants, GLM-4.5V, GPT-5.4, Claude-Opus-4.7, and Gemini-3.1-Pro. The models often solve coarse binary AWB judgments, but they remain weak on numeric CCT estimation and on some fine color-difference judgments. On ColorChecker-24 stimuli, the three closed-weight frontier models reach CCT MAE of 715-1056 K, compared with 1358-2133 K for the five open-weight models. A non-ColorChecker control shows that this advantage is partly template-dependent. The results suggest that current MLLMs have useful color words and coarse visual priors, but their color judgments are not reliably calibrated to CIE-computable color differences.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40210

AcrossDEX 1.0: From Human Motion Pretraining to Bimanual Dexterous Manipulation across Hand Embodiments

Xiaoyu Yang, Nan Wu

原文摘要

Bimanual dexterous manipulation requires continuous coordination of wrist motion, finger contact, and object motion. Human videos provide rich manipulation experience. Using this experience for robot control requires aligning human poses with robot commands and accounting for embodiment-specific kinematics and contact dynamics. We present AcrossDEX 1.0, a learning system that connects human motion pretraining, simulation-based expert learning, robot demonstration collection, and visual closed-loop execution. Pretraining on HOT3D Aria predicts one second of bimanual motion from five images and thirty annotated hand states over the preceding second. Robot adaptation preserves the visual encoder, temporal backbone, and wrist parameters. Shared wrist representations, separate finger fields, and validity masks support both six-channel Inspire hands and sixteen-joint Allegro hands. The robot policy predicts sixty control targets from frontal images, command history, and task conditions. It executes a prefix and replans from updated observations. We compare direct regression, diffusion, and flow matching on lid opening and return and closed-lid object reorientation. Direct regression achieves success rates of 40.6\% for opening and return, 100.0\% for Inspire reorientation, and 93.3\% for Allegro reorientation. Flow matching achieves 90.0\% on Allegro reorientation. Paired comparisons further show that constraining replanning with the previous plan improves the continuous execution of generative policies. These results demonstrate a common adaptation pipeline for two hand embodiments and highlight the roles of contact coordination and action-chunk continuity.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40207

RoboAtom: Large-scale Atomic-Action Supervision for Robot Learning

Xueyuan Wei, Xuanxu Wang, Xudong Li, Yuping He, Wanshui Gan, Jiaqi Peng, Wenqi Guo, Jianjun Zhou 等 13 位作者

原文摘要

Fine-grained action annotations can support skill reuse and compositional generalization in robot policies. However, robot datasets typically provide task-level instructions without subtask annotations. Although some include subtask labels, inconsistent formats and conventions hinder cross-source joint training. We propose RoboAtom-Data, which adds unified, time-aligned atomic-action annotations to existing data from multiple sources, covering 1.45 million trajectories, 6.88 million skill-labeled segments, and 16,882.1 hours. Our pipeline combines a unified protocol, large-scale manual annotation, propagation across repeated executions with the same ordered skill sequence, and multi-stage quality control. We evaluate the dataset through automatic atomic-action annotation and robot control. We construct RoboAtom-Bench to standardize evaluation of skill recognition and temporal boundary localization. Trained on the annotated data, RoboAtom-Anno achieves better automatic annotation performance than all evaluated open- and closed-source models on both RoboAtom-Bench and the external WGO-Bench. For robot control, atomic-action supervision paired with hierarchical execution improves task success over task-level baselines on LIBERO-Long, LIBERO-Plus, and RoboTwin. We will release the data, benchmark, model, and construction pipeline to support further research on skill-level robot learning.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40204

Attack-Resilient Multi-Bit Image Watermarking Framework via Latent Coordinate Sign Clamping

Marjan Beheshti, Ronghua Xu

原文摘要

Watermarking is essential for image copyright protection and attribution, yet existing methods suffer from fundamental trade-offs among post-hoc applicability to pre-existing images, multi-bit capacity, training-free deployment, and adversarial resilience. To address these limitations, we propose a training-free watermarking framework that exploits the overcompleteness of diffusion latent spaces to embed multi-bit payloads into arbitrary images while preserving high visual quality. Additionally, we develop a three-layer decoding pipeline that combines magnitude-weighted majority voting, BCH, and Chase decoding to maximize message-extraction accuracy in the presence of channel noise. To counter active adversaries, our framework integrates a steganalysis-resistant noise camouflage layer and a dual-layer forgery defense that combines perceptual hashing with a Reed-Solomon fuzzy commitment scheme over CLIP features. Empirical evaluations demonstrate that our method applies to both natural and AI-generated images with a scalable $32\text{--}128$-bit capacity. Furthermore, it effectively mitigates advanced removal vectors ($94.6\%$ decode rate against CtrlRegen+ regeneration attacks) and secures robust forgery detection ($98.8\%$ accuracy via joint CLIP and RS fuzzy commitment mechanism).

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2405.19005

AdalReID: Auto-selected Knowledge Adapters for Lifelong Person Re-identification

Xuelin Qian, Ruiqi Wu, Zhongling Huang, Dingwen Zhang, Junwei Han

原文摘要

Lifelong Person Re-Identification (LReID) extends traditional ReID by requiring systems to continually learn from non-overlapping datasets across different times and locations, adapting to new identities while preserving knowledge of previous ones. Existing approaches, either rehearsal-free or rehearsal-based, still suffer from the problem of catastrophic forgetting since they try to cram diverse knowledge into one fixed model. To overcome this limitation, we introduce a novel framework AdalReID, that adopts knowledge adapters and a parameter-free auto-selection mechanism for lifelong learning. Concretely, we incrementally build distinct adapters to learn domain-specific knowledge at each step, which can effectively learn and preserve knowledge across different datasets. Meanwhile, the proposed auto-selection strategy adaptively calculates the knowledge similarity between the input set and the adapters. On the one hand, the appropriate adapters are selected for the inputs to process ReID, and on the other hand, the knowledge interaction and fusion between adapters are enhanced to improve the generalization ability of the model. Extensive experiments are conducted to demonstrate the superiority of our AdalReID, which significantly beats SOTAs by about 5\% and 3\% mAP on seen and unseen domains.

cs.CV

查看论文
arXiv ↗PDF ↗