跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 09:03 — 2026-11-16 09:03(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:2026-11-16 01:34最近发现新增版本:2026-11-14 15:09库内论文最新更新时间:2026-11-13 02:59

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

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

浏览论文库

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 23,348 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.14965

Early Signals, Strong Decisions: Prefix-Guided Sampling for Parallel Test-Time Scaling

Jie Ren, Jonathan Rosenfeld, Neil Thompson

原文摘要

Parallel test-time scaling (TTS) has been shown to enhance reasoning in large language models by generating and aggregating multiple independent reasoning paths. Internal confidence scores can further improve this process by identifying paths of varying quality. However, existing methods remain computationally inefficient, as low-quality paths are fully expanded before being evaluated. In this work, we aim to improve the use of internal confidence signals for better model performance and computational efficiency. We begin by offering a new perspective on the role of confidence in aggregation, showing that it is most impactful for questions near the decision boundary. Notably, when amplified by multi-sample aggregation, even small confidence signals derived from short prefixes can meaningfully influence outcomes in these boundary cases. Building on this insight, we introduce Prefix-Guided Sampling (PreG), a method that reallocates computation by first generating short prefixes, ranking them using internal confidence scores, and then completing only the most promising candidates. This strategy reduces token usage while maintaining gains in path quality. We provide theoretical analysis demonstrating that, under a fixed compute budget, PreG strengthens the effective signal by widening the decision boundary margin. Empirically, our method consistently outperforms standard parallel TTS approaches across benchmarks, while significantly improving token efficiency and reducing overall computation.

cs.AI

新论文 · v1arXiv:2611.14963

GHA-SmellFix: Taking Action with Agentic LLMs for Detecting and Refactoring GitHub Actions Workflow Smells

Anderson Uchôa, Jhefferson Souza, Emanuel Ávila, Gabriel Silva, Kevin Lira, Hui Sun, Nelson Araújo, Arthur Cordeiro 等 10 位作者

原文摘要

Continuous integration and continuous delivery workflows are key artifacts in software projects. In GitHub Actions, they encode build, test, release, deployment, and security automation in YAML. These workflows contain configuration smells affecting security, reliability, maintainability, or operational stability. Existing approaches are mostly rule-based, with rules hard to create and evolve, and typically report findings without fixes. Agentic LLM pipelines can combine contextual detection, transformation selection, and patch generation. Specialized agents can gate refactoring on positive detection verdicts, potentially avoiding unnecessary changes, but it is unclear whether decomposition improves effectiveness or mainly changes overhead. We present GHA-SmellFix, an agentic LLM pipeline for detecting and refactoring GitHub Actions workflow smells. We compare two designs: Joint, where one agent detects and refactors, and Decomposed, where separate agents detect and then refactor. We operationalize 19 smells from an existing catalog with explicit detection criteria, refactoring expectations, exclusion rules, and safety checks, and curate a ground truth of 1,710 (workflow, smell) pairs. We evaluate the designs with four LLMs (GPT-5.4-nano, Gemini 3.5 Flash, Claude Haiku 4.5, and DeepSeek V4 Flash) on 570 sampled pairs. Results show that decomposition does not universally improve patch quality; its main benefit is controlling when patch generation is attempted. It helps models prone to missing smells and can reduce overhead by gating patches. Once a smell is correctly detected, clean refactoring is generally effective, making detection the main end-to-end bottleneck. However, false positives can trigger unnecessary edits to execution-relevant constructs. Practical CI/CD agents thus need reliable abstention and construct-aware validation alongside patch generation.

cs.SE · cs.MA

新论文 · v1arXiv:2611.14962

FIRE: Failure Isolation and Reliability for Production-Connected Experiments at Scale

Shripad Nadgowda, Gaurav Mitra, Sing Sing Ma, Vipul Chaskar, Pradipta Ghosh, Canturk Isci, Onkar Deshpande, Edgardo Aviles-Lopez 等 10 位作者

原文摘要

Pre-production changes are usually tested in isolated environments to prevent their side effects from reaching production. Some record-and-replay platforms allow a production-connected mode: candidate changes receive recorded production requests while selected downstream calls reach production dependencies. This improves fidelity before deployment, but it also introduces reliability risks. At hyperscale, experimental traffic can fan out across shared services, trigger latent defects, or send malformed input to systems serving user requests. In this paper, we show how production-connected experimentation can operate reliably in a large-scale recommendation serving system. To contain downstream effects without sacrificing realistic dependency behavior, the platform uses three complementary guardrails. Isolated tiers redirect replay traffic away from shared dependencies where replication is practical. Dependency monitors observe downstream health and experiment-attributed errors and terminate experiments after sustained violations. Traffic pinning limits experimental calls to a designated subset of downstream workers when full replication would require scarce capacity. Isolated ranking tiers process billions of replayed requests per day using under 1% of the corresponding serving capacity. Over 90 days, these tiers experienced more than 200,000 abnormal worker exits without directly affecting production-serving workers. During a separate three-month window, dependency monitors cancelled approximately 5% of experiments for the measured ranking service and accounted for 87% of its cancellations. Dependency-aware triggering also reduced code-review experiment executions by 25%. These results show that high-fidelity, production-connected experimentation can operate at scale when downstream effects are isolated where possible, bounded where necessary, and continuously monitored and attributed.

cs.SE · cs.DC

新论文 · v1arXiv:2611.14961

CommJEPA: When Predictive Representation Learning Meets Wireless Intelligence

Feiran You, Hongyang Du, Kang Wei, Jun Li, Abbas Jamalipour

原文摘要

Artificial intelligence (AI) is becoming an integral part of wireless systems, yet much of today's wireless AI remains task-specific and reactive, with models typically trained to map current observations to predefined outputs or reconstruct observed data. While effective for individual tasks, such approaches provide limited support for learning what is predictable, reusable, and transferable in dynamic wireless environments. Joint-Embedding Predictive Architecture (JEPA) offers a different perspective by learning predictive representations in latent space that capture informative structure in the observations. In this article, we introduce Communication JEPA (CommJEPA) as a communication-oriented framework for predictive representation learning. The central idea is bidirectional. JEPA can equip wireless systems with predictive representations for capturing latent channel and environmental dynamics, integrating heterogeneous observations, adapting to changing conditions, and supporting future decisions. Conversely, the physical structure, partial observability, multiple time scales, action-dependent evolution, and resource constraints of wireless systems motivate new communication-aware JEPA designs. We develop this mutual perspective, organize the resulting design space, and discuss representative JEPA-based wireless instantiations for prediction and control. We further highlight open challenges toward scalable, interactive, and predictive wireless intelligence.

cs.NI

新论文 · v1arXiv:2611.14960

Termination Lag: Coding Agents Solve Early but Stop Late

Musa Cim, Burak Topcu, Mahmut Taylan Kandemir

原文摘要

Coding agents can solve a task well before they stop working on it. We characterize \emph{termination lag}--the number of steps between an agent's first correct patch and the end of its run--across five models, two agent frameworks, and three SWE-bench datasets by recording and testing every distinct repository patch generated during execution. Our analysis reveals that 38--82% of successful runs achieve a correct solution on their initial source-code edit. However, agents continue to expend substantial effort after correct patches, with post-solution steps accounting for a median of 35--37% for Qwen3-Coder and 54--60% for Laguna-XS.2 in successful runs on SWE-bench Verified and Multilingual. Agents spend most of these additional steps verifying their work and exploring the repository. In a small fraction of cases (1--8%), this continued activity leads agents to undo their earlier correct patch, leaving the final solution incorrect.

cs.AI · cs.CL

新论文 · v1arXiv:2611.14959

The hidden solar cost of urban unfamiliarity

Lijia Liu, Yimeng Song

原文摘要

Unfamiliar walkers may follow the shortest route and miss nearby shade, indoor passages and multilevel connections. We define the resulting hidden solar cost as the direct-sun exposure avoidable through shade-informed routing without substantial detours. We developed a time-specific three-dimensional model of Hong Kong Island that combines indoor and outdoor walking networks with building geometry, vegetation mapped by light detection and ranging (LiDAR), and solar position. For 500 modelled journeys, we compared shortest and shade-informed routes at four daytime snapshots and five extra-distance limits. At noon, shade-informed routes reduced modelled direct-sun exposure by 13.5% relative to shortest routes under a 10% extra-distance limit. Route length increased by 2.85% on average. A 5% extra-distance limit delivered 77% of the reduction obtained at 10%. In a controlled comparison, outdoor shade information accounted for 86% of the reduction and indoor-protection information for 14%. Removing multilevel connections left only 191 of 500 journeys feasible within the original route-length limit. These route comparisons identify an avoidable solar cost when existing protection is missing from the information used to choose a route. Making protected routes visible and preserving their connections can reduce sun exposure without large detours.

cs.CY

新论文 · v1arXiv:2611.14958

Adapting Monocular Depth Estimation in Novel Scenes through Disparity Refinement and Robot Ego-Motion

Dimitrios Chatziparaschis, Georgios Georgakis, Adnan I. Ansar, Shehryar Khattak, Konstantinos Karydis

原文摘要

The geometric understanding of a scene is a crucial component for safe and efficient robotic operations in novel and unstructured environments. The recent emergence of foundation models for Monocular Depth Estimation (MDE) has provided an opportunity to enrich robotic perception capabilities with dense long-range depth predictions, replacing expensive onboard hardware (e.g., LiDARs and stereo cameras). However, these offline models are primarily trained on affine-invariant depth representations, and their generalization to novel scenes remains unclear. In this work we present EM-ViT, a monocular depth estimation model that learns to adapt online relative depth inputs from a foundation model prior to the metric scale with observations collected during robotic operations. Motivated by the stereo camera parameterization, our method decomposes depth prediction via dense disparity refinement to recover the scene's relative structure and an effective baseline scalar prediction to determine the missing metric scale. The learning process leverages sparse LiDAR points and, optionally, the robot's Ego-Motion (EM) to rapidly train a lightweight Vision Transformer (ViT), while an internal gradient matching loss preserves the fine-grained semantic structure of the input disparity in real-time. We demonstrate the efficacy of our method on publicly available sequences, such as KITTI, and show that our online learning pipeline can adapt to novel scenes faster and with higher accuracy than existing MDE foundation models. The code and supplementary materials will be publicly available at https://emvit-mde.github.io.

cs.RO · cs.CV

新论文 · v1arXiv:2611.14956

Binding Mode Matters: Hotspot-Aware Drug Discovery via Explorative Preferences

Dingshuo Chen, Hao Yang, Kuangqi Zhou, Zhixun Li, Qiang Liu, Xiangxiang Zeng, Shu Wu, Yaosen Min

原文摘要

Discovering hit molecules requires not just high binding affinity, but also the identification of diverse binding modes, which are critical for experimental assays. Existing generative approaches have predominantly relied on optimizing a scalar docking score, obscuring the distinct contributions of key binding determinants. To this end, we introduce a paradigm shift by formulating target-based drug design as a multi-objective exploration task, where each objective explicitly corresponds to enhancing interactions with a specific hotspot. Here, we introduce BindMol, a novel generative framework driven by a customized multi-objective reinforcement learning algorithm. By incorporating explorative preferences during training, our approach efficiently uncovers molecules with diverse and desirable binding profiles. Empirical results demonstrate that BindMol facilitates the discovery of high-affinity compounds characterized by both structural novelty and diverse binding modes. Validated across target-based drug discovery and multi-property optimization tasks, our approach provides a versatile paradigm for goal-oriented drug discovery.

cs.LG · cs.AI

新论文 · v1arXiv:2611.14955

The Posterior-Prior Epistemic Gap: When World Model Imagination Fails to Carry Task-Relevant Signals

Jaerock Kwon, Elahe Delavari, Donghyun Kim, Haewoon Nam

原文摘要

Model-based planners that roll out imagined futures assume the transition model faithfully propagates task-relevant signals---a property rarely measured directly. In a single-seed case study of a Recurrent State Space Model world model with active-inference planning in the CARLA driving simulator, we identify a \textbf{posterior-prior gap}---posterior (observation-filtered) states retain obstacle information that imagined rollout states progressively lose: a supervised obstacle probe achieves AUC 0.85 on posterior states, but the same probe applied to imagined prior states shows monotonic decay (AUC 0.85$\rightarrow$0.71 over 15 steps; logit separation drops 57\%). Because the probe is identical, the decay isolates the transition model---not the representation---as the information bottleneck. Obstacle avoidance drops to 0\% without privileged runtime coordinates, and the planner's own ensemble-based epistemic term does not flag the loss---ensemble disagreement yields AUC 0.52 as an obstacle classifier (chance level), making the failure an unflagged imagination failure---an unknown unknown at planning time. As a secondary contribution, we show that \textbf{task-conditioned weighting of Effective Free Energy components} over the same world model yields lane keeping ($81.2 \pm 1.8$\% route completion) and obstacle avoidance (28/28 avoided, \emph{using privileged coordinates}) in the CARLA simulator, with runtime weight modulation enabling post-evasion centering.

cs.RO · cs.AI

新论文 · v1arXiv:2611.14953

RSLiveBench-UAV: A Continually Evolving Vision-Language Benchmark for Aerial Spatial Intelligence

Yue Zhou, Jiawei Liu, Jue Chen, Ziyang Gong, Haojia Wei, Jingxiang Li, Xue Jiang, Zhihang Zhong 等 12 位作者

原文摘要

Aerial spatial intelligence (ASI) requires models to understand objects and spatial relationships across changing viewpoints and scales. Evaluating these abilities as models evolve calls for fresh physical observations, yet producing new aerial spatial questions requires repeatedly establishing entity identities, geometric references, and cross-view correspondences. We introduce \textbf{RSLiveBench-UAV}, a continually evolving vision-language benchmark driven by recurring acquisition of real UAV imagery. Its update protocol admits images captured after the preceding release and delays answer disclosure. An entity-centered production workflow uses geometry-assisted association to link repeated observations of physical vehicles, reuse human-verified attributes, and combine them with view-specific annotations and spatial references for traceable question generation. All tasks use deterministic scoring without model judges. We evaluate 30 general-purpose, remote-sensing, and embodied models on 35,491 question records from ten scenes, covering 17 tasks across 2D perception, 3D perception, cross-view perception, and reasoning. All 18 tested embodied models outperform the three selected remote-sensing comparators in Overall, although the strongest embodied model scores 43.29 versus 59.88 for GPT-6-Astra. Fine-grained vehicle recognition remains challenging, and performance varies across heights and camera pitches. Retrospective scene-group comparisons and rolling-window replay characterize score-pattern consistency under scene renewal. RSLiveBench-UAV connects fresh physical observations, entity-centered answer production, and systematic model evaluation to support continual assessment of ASI. Benchmark will release at https://rslivebench.space

cs.CV

版本更新 · v3arXiv:2603.05868

AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models

Hyeongjun Heo, Seungyeon Woo, Sang Min Kim, Junho Kim, Junho Lee, Yonghyeon Lee, Young Min Kim

原文摘要

Despite remarkable progress in Vision-Language-Action models (VLAs) for robot manipulation, these large pre-trained models require fine-tuning to be deployed in specific environments. These fine-tuned models are highly sensitive to camera viewpoint changes that frequently occur in unstructured environments. In this paper, we propose a zero-shot camera adaptation framework without additional demonstration data, policy fine-tuning, or architectural modification. Our key idea is to virtually adjust test-time camera observations to match the training camera configuration in real-time. For that, we use a recent feed-forward novel view synthesis model which outputs high-quality target view images, handling both extrinsic and intrinsic parameters. This plug-and-play approach preserves the pre-trained capabilities of VLAs and applies to any RGB-based policy. Through extensive experiments on the LIBERO benchmark, our method consistently outperforms baselines that use data augmentation for policy fine-tuning or additional 3D-aware features for visual input. We further validate that our approach constantly enhances viewpoint robustness in real-world robotic manipulation scenarios, including settings with varying camera extrinsics, intrinsics, and freely moving handheld cameras. Project Page: https://heo0224.github.io/AnyCamVLA/

cs.RO

新论文 · v1arXiv:2611.14952

JoyFrontBench: Evaluating Front-End Coding Agents through Goal-Oriented Acceptance Contracts

Xiaoyi Qiao, Yicheng Wang, Jianan Lin, Xiaoyang Ji, Dongyi Lv, Yidan Huang, Shi Suo, Shiying Fan 等 10 位作者

原文摘要

Front-end coding agents are expected to produce applications that fulfill user goals, yet high task scores can coexist with failures in essential workflows. Evaluating these agents therefore requires an explicit distinction between partial implementation and application success. We introduce JoyFrontBench, a benchmark that makes this distinction through goal-oriented acceptance contracts. Each contract identifies core tasks and mandatory criteria before generation: a core task passes only when all mandatory criteria are satisfied and a shared completion threshold is met, while application success requires every core task to pass on the same operational artifact within a single run. Derived from practitioner requirements, JoyFrontBench comprises 100 front-end development problems, 764 tasks, and 2,596 atomic criteria, with reviewed annotations linking user goals to core tasks and evidence requirements. The evaluation framework combines evidence-grounded judgments with deterministic record auditing and fixed scoring rules, preserving graded task assessment alongside explicit core-task and application-level acceptance. We evaluate five coding models under two agent harnesses, OpenHands and OpenCode, on the 70-problem test set; the remaining 30 problems form a public set for validation and diagnostic analyses. Under OpenHands, the mean Average Task Score (ATS) across models is 87.69%, while the mean Application Success Rate (ASR) is 51.52%. Further analyses reveal changes in model rankings across harnesses and variation in application success across repeated runs. These findings highlight the limitations of aggregate task scores in characterizing application success and motivate explicit assessment of core-goal fulfillment alongside graded task performance.

cs.SE

版本更新 · v2arXiv:2609.04726

Bridging Modalities and Tasks: A Unified Hierarchical ViT for SAR-to-Optical Translation and Semantic Segmentation

Siyuan Liu, Xuze Zhang, Yongshun Wang, Licong Pan, Hang Liu, Huihui Li

原文摘要

Synthetic Aperture Radar (SAR) remains available through cloud and darkness, yet speckle and non-intuitive scattering make it hard to inspect and interpret. SAR-to-optical (S2O) translation renders radar observations as optical-like images for visual access, while semantic segmentation on SAR remains necessary since land-cover decisions cannot rely on synthesised pixels. We propose BMT, a hierarchical Vision Transformer coupling both tasks on a shared encoder via multi-scale one-hot conditioning, a gated LocalViTBlock, a colour-calibrating generation head, ControlNet-style zero-initialized injection, and uncertainty-based task weighting. The joint framework's value is not label-free training: it uses paired optical images and the same pixel annotations as a dedicated SAR segmentor, supervising the SAR decoder and teacher-forcing the generator with ground-truth one-hot maps. At test time, the model takes only SAR and returns an optical-like readout and a radar-decided land-cover map, with the translation objective supplying dense appearance supervision that speckle lacks. On WHU-OPT-SAR, the predicted-condition model achieves the best SSIM and PSNR among compared translators; its land-cover map surpasses the same backbone trained for labelling alone and is within about one point of DeepLabV3+.

cs.CV

版本更新 · v2arXiv:2610.10238

Geometry-Supervised Visual Representation Learning for Multi-Phenotype Lesion Interpretation in Medical VLMs

Hao Wang, Qiwei Zeng, Shuchang Ye, Jinghao Lin, Yuezhe Yang, Yige Peng, Jinman Kim, Lei Bi

原文摘要

Medical vision-language models (VLMs) have shown increasing potential for clinical image interpretation. However, these models still struggle to interpret multi-phenotype lesions whose diagnosis requires the joint assessment of multiple pathological phenotypes. Existing vision-language alignment methods produce visual representations that fail to preserve anatomical hierarchies and relationships among phenotypic subclasses. This stems from their reliance on semantic supervision, which lacks geometric constraints to preserve these relationships in the visual embedding space. Moreover, the sparsity of lesion-related anatomical and phenotypic representations makes it difficult for medical VLMs to capture important diagnostic evidence. To address these limitations, we propose \textbf{PureVision}, a geometry-supervised visual representation learning framework for multi-phenotype lesion interpretation in medical VLMs. It combines a geometry-supervised representation learning module, \textbf{PureEyes}, and an anatomy-guided evidence aggregation module, \textbf{PureNeurons}. PureEyes provides geometric supervision through ideal spatial distributions that encode anatomical hierarchies and phenotypic subclass relationships. PureNeurons projects visual representations into the learned latent space, using their positions to selectively aggregate lesion-specific anatomical and phenotypic evidence. Experiments on \textit{LIDC-IDRI}, \textit{CBIS-DDSM}, and \textit{3DReasonKnee} demonstrate that PureVision improves lesion grounding and phenotype characterization in visual question answering and radiology report generation. Code is available at: https://anonymous.4open.science/r/purevision-06C2.

cs.CV

新论文 · v1arXiv:2611.14950

Stress-Testing Sandbagging Detection Under Adaptive Attack

Bhoj Rani Soopal, Aarohi Agrawal, Josh Karthikeyan, Edward Lue Chee Lip

原文摘要

Developers, auditors and researchers read evaluation scores as evidence of what a model can do. A model that sandbags, scoring low on purpose while keeping the capability, turns a low score into false reassurance. Sandbagging detectors are usually tested once against a fixed attack, but a real attacker sees what gets flagged and adapts. We build sandbagging models by fine-tuning small open-weight models to fail math word problems (GSM8K) they can otherwise solve, but only when an audit marker is in the prompt. On Qwen 2.5-3B, we adapt the attack over two retraining rounds against a text-based audit. Two rounds of retraining cut the text audit's AUC from 0.978 to 0.560 while the marker still removes 40-49 points of accuracy. The attack worked in 7 of 8 retrained seeds, and the audit missed every retraining (AUC 0.451-0.576), including one Llama run. Activation probes also flag 99% of benign fine-tunes' examples, and matched probes transfer to only 1 of 5 held-out training runs. Eight further trigger attacks are all active under their own prompt but not under the detectors' prompt. A detector that catches a fixed attack has not been shown to catch an adaptive one.

cs.CR · cs.LG

版本更新 · v2arXiv:2610.24206

SWE-Bench Pro V2: A Cleaner, Harder-to-Game Coding Benchmark

Soham Dan, Jeff Da, Sanyam Bhutani, Miguel Romero Calvo, Ivan Guevara, Fernando Carabedo, Jose Bernal, Julio Reyna 等 11 位作者

原文摘要

SWE-Bench Pro is a widely used benchmark of long-horizon software engineering tasks for coding agents. As agents improve, they reach task issues earlier agents never touched and interact with the evaluation environment in ways the original harness did not anticipate. We present SWE-Bench Pro V2, a revised public split built to keep the benchmark accurate as capabilities advance. Agentic audits, expert adjudication and blind re-implementation repaired or retired 480 of the 731 tasks: 23 contracted engineers spent 404 hours, each working in a language they write professionally, and every revised instruction was verified by a second engineer solving the task from the text alone. A hardened protocol restricts network access to the model endpoint and re-grades every patch in a clean container, so agents cannot retrieve upstream fixes or get credit for changes outside their patch. On the 642 V2 tasks frontier agents resolve up to 99.4% while other systems stay clearly separated, and a 51-task Hard split spreads systems from 52.9% to 98.0%. We release the benchmark and distill lessons for maintaining agent benchmarks over time.

cs.SE · cs.AI

新论文 · v1arXiv:2611.14949

RSI-PDEbench: A Benchmark for Self-Improving Agents in PDE Solving

Binghang Lu, Lang Cao, Changhong Mou, Yige Sun, Cindy Xiangrui Kong, Zheyuan Deng, Tian Yuan, Bing Hu 等 11 位作者

原文摘要

Identifying and solving partial differential equations (PDEs) from sampled solution data often requires substantial expert effort in equation discovery, coefficient estimation, and numerical solver configuration, especially under noise and distribution shifts. Can large language model (LLM) agents automate this workflow accurately and efficiently? To investigate this question, we introduce \bench{}, a benchmark of 1,001 cases spanning 42 equation templates, including both classical and fractional PDEs. It provides three evaluation settings: Full evaluates performance on noise-free solution data; Noisy tests robustness to Gaussian noise with an RMS equal to 50\% of the clean-signal RMS; and Hard-OOD tests challenging out-of-distribution generalization to unseen equation templates and shifted coefficient ranges. We further introduce RSI-PDE, a recursively self-improving agent harness that shortlists candidate equations by residual loss, uses relative $L^2$ feedback to refine coefficients and numerical solvers, and applies a validation gate to policy and memory updates. We compare RSI-PDE with single-run baselines and native agent harnesses (Claude Code or Codex) across four frontier models. Across the three settings, RSI-PDE improves the pass rate averaged across the four models by 106.5--181.9\% relative to single-run baselines and by 3.0--19.6\% relative to native harnesses, while reducing total recorded model calls by 46.9\% across the 12 model--setting pairs. These results highlight the potential of validated recursive self-improvement in LLM agents to advance scientific computing.

cs.AI

版本更新 · v2arXiv:2509.21284

Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and Beyond

Dingzirui Wang, Xuanliang Zhang, Keyan Xu, Qingfu Zhu, Wanxiang Che, Yang Deng

原文摘要

Existing research indicates that the output of Chain-of-Thought (CoT) is significantly affected by input perturbations. Although many methods aim to mitigate such impact by optimizing prompts, a theoretical explanation of how these perturbations influence CoT outputs remains an open area of research. This gap limits our in-depth understanding of how input perturbations propagate during the reasoning process and hinders further improvements in prompt optimization methods. Therefore, in this paper, we theoretically analyze the effect of input perturbations on the fluctuation of CoT outputs. We first derive an upper bound for input perturbations under the condition that the output fluctuation is within an acceptable range, based on which we prove that: (i) This upper bound is positively correlated with the number of reasoning steps in the CoT; (ii) Even an infinitely long reasoning process cannot eliminate the impact of input perturbations. We then apply these conclusions to the Linear Self-Attention (LSA) model, which can be viewed as a simplified version of the Transformer. For the LSA model, we prove that the upper bound for input perturbation is negatively correlated with the norms of the input embedding and hidden state vectors. To validate this theoretical analysis, we conduct experiments on three mainstream datasets and four mainstream models. The experimental results align with our theoretical analysis, empirically demonstrating the correctness of our findings.

cs.CL

新论文 · v1arXiv:2611.14947

One Block Is Enough: LoopMR for Accelerated MRI Reconstruction

Yimeng He, Yibin Xie, Yi Zheng, Yifan Gao, Lixia Wang, Yin-Chen Hsu, Yufeng Wang, Meng Lu 等 10 位作者

原文摘要

Deep-learning unrolled networks are the leading approach to accelerated MRI reconstruction. State-of-the-art models such as PromptMR+ learn a distinct block for every cascade, so their size grows with the number of cascades. Sharing one block across iterations avoids adding parameters, but earlier shared-weight models typically used a tiny block and produced worse images than models with distinct weights. Therefore, it remained unclear whether weight sharing itself or the choice of block was the problem. Recent advances in looped transformers, which reuse the same block across layers, show that they can match or outperform their distinct-weight counterparts on several tasks. Motivated by this, we propose LoopMR, which reuses a single Restormer block at every iteration as its core. Besides the current image estimate, the block receives data-consistency inputs and latent images. On four datasets covering the brain (CC359), knee (fastMRI), heart (CMRxRecon2023) and carotid (in-house), LoopMR significantly outperforms E2E-VarNet, PromptMR and PromptMR+ in PSNR and SSIM at every acceleration factor (p < 0.01), with about 1/9 of PromptMR+'s parameters (10.3M versus 92.9M). It also keeps its lead at unseen acceleration factors and on an unseen dataset. With our transformer block, the shared model matches or outperforms its distinct-weight counterpart at 6, 12 and 24 iterations. At a fixed number of iterations, shared transformer blocks match or outperform their distinct-weight versions, while shared CNN blocks perform worse. These results suggest that looping one well-chosen block can outperform stacking distinct cascades in MRI reconstruction, with a fraction of the parameters.

eess.IV · cs.CV

新论文 · v1arXiv:2611.14946

LOHRE: Execution-Grounded Type Recovery via LLM-Orchestrated Hybrid Analysis

Hao Jiang, Yujie Yang, Tao Li, Chenhui Cui, Liangfeng Xu, Chengjie Liu, Weiping Wen, Rubing Huang 等 9 位作者

原文摘要

Documenting stripped binary functions for security analysis requires recovering function interfaces and user-defined type (UDT) layouts from machine code. Existing large language model (LLM)-based methods face two limitations: they lack execution-based validation to detect inferred UDTs inconsistent with actual memory layouts, and may overlook evidence about shared UDTs across functions without direct call relationships. We present LLM-Orchestrated Hybrid Reverse Engineering (LOHRE), a framework that treats inferred UDTs as falsifiable hypotheses and tests them against program execution. LOHRE uses a hypothesize-validate-refine loop to test candidate layouts through paired dynamic slice emulation of baseline and mutated inputs. To reduce the cost of processing lengthy execution histories, the Execution-Depth Heuristic (EDH) compresses paired traces into an execution-depth difference and a summary of the tested field's observed uses. A cross-function knowledge base aggregates compatible UDT hypotheses and field-level confidence scores to guide testing and hypothesis refinement. We evaluate LOHRE on RealType at four optimization levels and a Windows remote procedure call (RPC) dataset. LOHRE achieves an average UDT Structural accuracy of 57.85% across RealType's four optimization levels and 35.6% on Windows RPC, outperforming the evaluated static baselines. Disabling dynamic validation reduces accuracy to 19.28% on RealType and 9.2% on Windows RPC. Removing the cross-function knowledge base reduces accuracy to 41.03% on RealType and 10.0% on Windows RPC. Replacing EDH's compressed feedback with full execution traces reduces recovery accuracy while increasing token use by 3.7 times and runtime by 3.0 times. These results indicate that execution-based validation, compact feedback, and cross-function evidence contribute to accurate and efficient UDT recovery.

cs.SE

新论文 · v1arXiv:2611.14945

Auriga: Harness-Governed LLM Agents for Effective Throughput Optimization in Execute-Order-Validate Permissioned Blockchains

Xiao Zhang, Tianyang Wang, Fangtao Gu, Haoxiang Sun, Puwei Wang, Jinchuan Chen

原文摘要

Effective throughput, the product of raw throughput and transaction success rate, determines the useful capacity of Execute-Order-Validate blockchains such as Hyperledger Fabric. Most prior work either tunes configurations to raise raw throughput, requiring many costly redeployments, or controls conflicts to raise the success rate, repairing them only after execution with kernel modifications. The few joint approaches tune only a small set of parameters and still rely on kernel changes to resolve conflicts. To address these challenges, we present Auriga, a non-invasive framework that jointly optimizes both factors through sample-efficient LLM-guided configuration search and pre-execution conflict prevention. A harness-governed multi-agent architecture coordinates LLM agents for parameter exploration, saturation-aware evaluation, and experience consolidation, with the harness controlling tool and memory access and retaining termination authority. For transaction scheduling, an LLM extracts symbolic AST templates from smart contracts offline. At runtime, the scheduler predicts read-write sets without executing them and partitions transactions into conflict-free groups. Across three benchmarks and conflict rates up to 70%, Auriga improves effective throughput by up to 6.0 times over default Fabric and 2.0 times over the strongest baseline. The tuning agent also discovers undocumented parameter dependencies, and ablation studies show the independent contributions of both subsystems.

cs.DB

版本更新 · v2arXiv:2602.08294

Not All Gap Correction Helps: A Geometric View of External Information in LLM Inference

Dingzirui Wang, Xuanliang Zhang, Keyan Xu, Qingfu Zhu, Wanxiang Che, Yang Deng

原文摘要

Providing external information beyond the query is a common way to improve large language model (LLM) inference, as seen in in-context learning (ICL), retrieval-augmented generation (RAG), and memory-based methods (Mem). Existing work increasingly suggests that useful external information should compensate for the gap between LLMs and user queries, implicitly assuming that stronger gap-correction can lead to better performance. In this paper, we challenge this assumption and show that more gap-corrective external information can instead harm performance. We analyze this phenomenon in Transformers through the lens of reasoning error, defined as the difference between the predicted answer vector and the ground-truth answer vector. Our analysis reveals that external information can be not only under-corrective but also over-corrective, where excessively strong correction increases reasoning error. We further show that the induced correction vector is jointly determined by attention and the complementarity between the external information and the query, and derive conditions under which information is properly corrective in both direction and magnitude. Experiments on four mainstream LLMs and seven reasoning benchmarks across ICL, RAG, and Mem validate our theory and support a theory-guided information selection method.

cs.CL

新论文 · v1arXiv:2611.14942

Emergent Vision-Shaped Thinking in Text-Only Reasoning through Multimodal Training

Qi Zhang, Bohan Wang, Qianru Sun, Hanwang Zhang

原文摘要

Does multimodal training shape how a language model thinks, even when the input is text only? We test this with targeted causal ablations across 10 multimodal configurations from 6 model families, with matched text-only backbones and cross-family transfer controls. We contrast spatial-imagery tasks that invite mental scene construction with symbol-manipulation tasks solvable by symbolic rules alone. We identify a vision-language axis in hidden-state space and ablate its projection at inference. In Chameleon-7B, this ablation drops accuracy on BIG-Bench Hard (BBH) navigate by 27.6 pp while leaving boolean expressions intact (+5.6 pp), a 33.2 pp double dissociation. The effect is direction-specific and layer-localized, extends to mental-simulation tasks such as mental rotation, paper folding, and perspective taking, and is not explained by task difficulty, reasoning depth, or sequential update load. Together, these results reveal emergent vision-shaped thinking (EVT): text-only reasoning that causally recruits representations introduced or strengthened by vision-language training, without assuming an image-like internal format. The measured effect is spatially concentrated at 7-8B and broadens to non-spatial visual attribute binding in the tested 32B configuration. In dual-path unified models (BAGEL, Janus-Pro), the causal handle localizes to the generation pathway as a compact one-dimensional carrier. The understanding pathway also encodes spatial information in a higher-rank, probe-decodable form, but is not the causal handle. To separate decodability from causal use, we analyze concentration, alignment, and semantic location. These diagnostics explain why behavior, probing, and intervention can diverge. Multimodal training thus reshapes the geometry of text-only reasoning, not just how visual input is processed.

cs.AI · cs.CV

版本更新 · v2arXiv:2605.21836

Modeling and Force Analysis of a Soft Linear Pneumatic Actuator

Mohammed Abboodi

原文摘要

Soft sleeve actuators (SSAs) have recently been developed as a pneumatic actuation approach for wearable and assistive robotic systems. By integrating the actuation structure into a sleeve-like geometry, these actuators can reduce reliance on external attachment layers and transmission mechanisms while maintaining compliance with limb-shaped surfaces. However, the force-generation behavior of SSAs remains insufficiently explained, particularly with respect to the variation of output force during extension, the influence of external loading, and the mechanical role of axial stiffness. This paper presents an analytical and experimental force analysis of a linear soft sleeve actuator (LSSA). A quasi-static analytical model was developed by expressing the net axial force as the pressure-generated contribution from the cap and folded walls, reduced by the force associated with axial stiffness. The model incorporates internal pressure, projected pressure areas, folded wall geometry, axial displacement, and an experimentally fitted axial stiffness relation. Prescribed-extension and static-load experiments were conducted to evaluate the actuator response. At 125 kPa, the generated force decreased from approximately 112 N at zero extension to nearly zero at 40 mm. Static loading delayed measurable force generation and reduced force output, particularly at low and intermediate pressures. The results show that LSSA force generation is governed by coupled effects of pressure, geometry, displacement, loading, and axial stiffness.

cs.RO

版本更新 · v2arXiv:2605.25109

Soft Pneumatic Actuators for Robotics: From Motion Generation to Performance Optimization

Mohammed Abboodi

原文摘要

Soft pneumatic actuators are widely used in soft robotics because they can produce large motions while remaining compliant enough to interact safely with objects, environments, and the human body. However, their performance is not solely determined by pressure. Instead, the response depends on the way the actuator is built, including the shape of its chambers, the placement of reinforcements, the use of folds, material stiffness, and the constraints that guide its deformation. As the literature has expanded, it has become more difficult to determine which mechanism is most suitable for a given application and which reported results can be compared across studies. This review examines soft pneumatic actuators according to the design strategies used to generate four motion classes: linear, bending, twisting, and omnidirectional actuation. For each class, it analyzes the structural features that define the deformation path, including braid angle, fold geometry, fiber orientation, chamber arrangement, structural asymmetry, and internal constraint layers. It then discusses how the design choice affect motion output, force generation, air demand, repeatability, durability, fabrication difficulty, and robotic integration. The review further identifies key conditions that must be considered when selecting or comparing actuators, including pressure, loading condition, actuator size, pneumatic supply, and hysteresis This approach helps explain why actuators with similar motion outputs may differ substantially in design requirements, pneumatic demand, and practical suitability. It also highlights the design priorities needed for compact, efficient, repeatable, and deployable soft pneumatic systems in wearable, biomedical, and mobile robotic applications.

cs.RO

新论文 · v1arXiv:2611.14941

Reality Perception Gap: Are AI-Manipulated Video Detectors Ready for the Real World?

Xiangrui Liu, Xinmiao Luan, Xinyuan Wang, Zhiyuan Fang, Chi-Yao Huang, Douglas C. Montgomery, Yanjie Fu, Felix Juefei-Xu 等 9 位作者

原文摘要

AI-manipulated video detectors are typically evaluated on clean, curated datasets. In deployment, however, videos have usually passed through repost compression on social-media platforms and sometimes were captured by imperfect hardware. To measure detection under these conditions, we introduce Reality Perception Gap (RPG), a benchmark of 10,000 videos from frontier generators and partially synthetic edits, processed with cross-platform repost compression and paired with real footage that carries camera-side optical artifacts. RPG also includes socially fragile content, such as crime and wartime footage, where fabricated videos can cause severe social harm. Across 18 detectors, none catches more than 15% of fakes at a 1% false-positive rate. A positive control and a re-encoding sweep separate two sources of failure: generator and content shift degrades detectors before any compression, and repost compression erases the low-level traces that the artifact-based detectors relies on. Existing detectors therefore struggle when deployment conditions strip away the generation artifacts they rely on. These complementary failures suggest that robust detection requires training under deployment conditions and combining low-level, temporal, and semantic evidence, where passive detection may have reached its limits.

cs.CV

新论文 · v1arXiv:2611.14940

TSBugs Explorer: Exploring and Benchmarking TypeScript Bugs

TianYi Tang, Saba Alimadadi

原文摘要

Curated datasets of real-world software bugs support empirical research in software testing, debugging, and automated program repair. However, exploring heterogeneous bug collections, comparing fault characteristics across projects, and constructing research-specific subsets often require manual inspection and custom scripts. We present TSBugs Explorer, an interactive visual analytics platform built upon our previously-published dataset of 633 bugs from 16 open-source TypeScript repositories, classified into 11 fault categories. The platform integrates bug records, repository characteristics, dependency information, and taxonomy guidance through coordinated visualizations, interactive filtering, and detailed bug inspection. It supports alternative aggregation and normalization of fault distributions, pairwise repository comparisons, and analysis of differences in observed fault profiles. An integrated benchmark builder allows researchers to select bug subsets using multiple criteria, inspect their composition, and export records in CSV or JSON format. We demonstrate the platform through three research workflows: fault characterization, cross-repository comparison, and task-specific benchmark construction. Functional validation by two authors confirmed selection correctness, visualization consistency, export integrity, and reproducibility across the tested workflows. By making the existing corpus easier to explore, compare, and reuse, TSBugs Explorer facilitates systematic, research-specific selection and export of TypeScript bug records.

cs.SE

版本更新 · v6arXiv:2610.03228

Reference-Compatible Parallel Execution for Quantized LLM Inference

Chengzhan Li

原文摘要

Batching a quantized large language model (LLM) can change full-vocabulary outputs and the key-value (KV) cache even when token positions and causal masks are unchanged. We introduce reference-derived phase plans: per-call execution descriptions that preserve a fixed deployment's producer, physical attention range, arithmetic and state ownership while exposing parallel work. Whole-graph plans split the complete computation at compatibility boundaries; local-attention plans split only attention and retain wider projection and feed-forward work. Independent arithmetic groups can also be packed into one operation without changing each group's reduction. We implement and qualify these paths on CUDA and Vulkan for Qwen, Llama and SmolLM2. On Linux/RTX A5000, compatible speculative execution reduces resident-service time by 17.21 percent, 25.54 percent and 11.52 percent relative to the fastest measured fixed target-only control for Qwen3-8B, Qwen3-14B and Llama-8B. Balanced experiments isolate an increment of 0.80 to 1.64 percent from Q8 projection packing and smaller, geometry-dependent gains from local cuts. For Qwen3-32B with mixed Q4_K/Q6_K weights, independent-channel grouping reduces ordinary service time by 5.61 percent against a graph-level scalar-column loop. Equal-work tests favor eight-query execution in aggregate, whereas complete live requests favor shorter proposals because longer proposals increase target work. The results show how to exploit known-query parallelism within an established numerical reference and how complete-request costs determine the useful execution strategy.

cs.PF

版本更新 · v2arXiv:2610.09074

TAP: Efficient Long-Horizon Agent Pruning via Trajectory-Anchored Recovery

Yuanzhe Li, Pengxin Wang, Yuxin Ren, Jianing Deng, Jingtong Hu, Song Wang, Jingdi Chen, Huanrui Yang

原文摘要

Emerging long-horizon agentic tasks require repeated model calls, worsening the inference cost of already-costly language models. While narrow agentic tasks suggest potential for aggressive model pruning without performance drop, empirical results show existing methods proposed for question answering tasks severely degrade task performance when applied to agentic models. We trace this failure to two decisions: what to prune and how to recover. For pruning, one-shot importance estimates fail to track how the pruned model adapts. For recovery, offline distillation covers only teacher prefixes, while full-trajectory on-policy distillation causes student errors to compound across turns. In this work, we propose Trajectory-Anchored Pruning (TAP), the first structural pruning framework for reinforcement learning (RL)-trained agents. TAP couples structural pruning with efficient on-policy recovery, anchoring interactions to teacher trajectories while allowing the student to generate each reasoning-action response. A frozen dense teacher supervises the student's response prefixes, addressing within-response training-inference mismatch while preventing student-induced deviations from propagating across training turns. Instead of one-shot pruning, TAP re-scores channels using gradients of the recovery objective on the recovered student, connecting iterative channel selection to the evolving policy. With 60% of FFN channels removed, TAP retains 99.2% and 88.0% of the dense 7B agents' task success rates on ALFWorld and WebShop, respectively, while reducing GPU time per successful task by approximately 22% and 17%. These results demonstrate effective structural compression of long-horizon agents under a limited recovery budget.

cs.LG

新论文 · v1arXiv:2611.14938

When Does a Recommendation Spark Curiosity? Theory, Measurement, and Field Evidence

Pan Li, Alexander Tuzhilin

原文摘要

Curiosity, the drive to close the gap between what one knows and what one wants to know, pulls consumers beyond their familiar content, sustains engagement, and breaks them out of the filter bubbles of repetitive, relevance-only recommendations. Despite its importance, curiosity is hardly incorporated into modern recommender systems for lack of a formal measure. The information-gap theory of curiosity provides no formal quantitative model that a recommender system can operate on, and existing proxy metrics do not accurately measure the curiosity that a recommended item evokes. To fill this research gap, we formalize the information-gap theory into five axioms of curiosity and construct the canonical formulation of a computational measure of the curiosity that a recommended item evokes in a consumer. We validate our curiosity measure through a survey-based study, in which it matches consumers' self-reported curiosity and outperforms alternative proxy metrics. We subsequently build a curiosity-aware recommender system that incorporates this measure into the utility function design, and we show through offline experiments on three real-world datasets that it significantly outperforms the state-of-the-art methods. Furthermore, we conduct a large-scale online controlled experiment at a major video-streaming platform in Asia, where we show that our method significantly increases click-through rate, video views, and time spent over the latest production system, leading to tangible economic impact for the company. Our method has since been deployed on the platform and remains in operation. Our findings establish consumer curiosity as a measurable and actionable objective for recommender systems, with important managerial implications for digital platforms to recommend what consumers wonder about.

econ.GN · cs.IR · cs.LG