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

+1200新增论文
+951其中 AI 相关
+132已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 16:53各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 17:00 — 2026-11-20 17:00(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:2026-11-20 08:48最近发现新增版本:2026-11-20 16:53库内论文最新更新时间:2026-11-20 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。

28,609 已收录论文23,738 AI 相关8,785 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 37 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.25429

Evolve Where It Matters: Coverage-Guided Self-Evolution of Agent Skills

Boyin Tan, Jiadong Zhang, Xiaosong Ma, Chun Jason Xue, Xiaowei Huang, Youcheng Sun

原文摘要

Agent skills package procedural knowledge as natural-language instructions, and a skill helps only when its instructions are correct and properly followed by the agent. Self-evolving agents revise their own skills from the runs they make, but existing methods judge each run as a whole, by its outcome or by where it went wrong, and cannot tell whether a failure comes from a wrong instruction or from one the agent did not follow. Instruction-level coverage was introduced to test skills and labels each instruction of a run as follow, not-follow, or not covered, which separates these causes. We leverage it for skill self-evolution with SkillPlumber, a framework in which an agent evolves its own skills where coverage shows they fall short. A persistent root cause analysis agent turns each label into a revision question and checks each revision against the next run, while a maintainer distills investigations across tasks into a shared strategy library. Across three benchmarks and three executors, SkillPlumber solves 64.7% to 70.5% of the tasks, 25.6 to 30.4 percentage points higher than the initial skill and 8.7 to 14.0 percentage points higher than the strongest baseline, and removing coverage reduces recovered failures by 20.8% on SkillsBench with GPT-5.5.

cs.CL · cs.AI

新论文 · v1arXiv:2611.25412

ChainAgent: Automated Chainable Vulnerability Discovery in PHP Web Applications

Xinyi Wang, Yeting Li, Shizhe Cui, Jiaming Guo, Qin Mai, Yecheng Sun, Hengyu Yang, Yujie Sun 等 12 位作者

原文摘要

High-impact attacks on PHP web applications often chain limited-capability vulnerabilities with other flaws or intended behaviors. Discovering these chains requires identifying flaws and the dependencies enabling capability composition. Existing vulnerability discovery techniques analyze flaws in isolation, while attack planning assumes known components. This separation makes it difficult to discover previously unknown components whose security relevance becomes apparent only through their potential roles in an exploit chain. We present ChainAgent, a goal-directed LLM-agent framework that jointly discovers exploit-chain components and their capability dependencies in source code. Guided by an empirical study of 386 real-world web exploit chains, ChainAgent represents vulnerabilities and functional gadgets--intended program behaviors that can be repurposed in attacks--through preconditions and capabilities over security-relevant objects. Instead of discovering vulnerabilities first and constructing attack paths afterward, ChainAgent uses an evolving exploit graph to guide source-code inspection. It searches backward from unmet preconditions for capability producers and forward from discovered capabilities for functional gadgets that consume or amplify them. Object-centered chaining knowledge from our empirical study directs searches toward promising vulnerability classes, functional operations, and object accesses. We evaluate ChainAgent against Codex, a general-purpose coding agent, on 15 PHP applications across three shared LLM backends. ChainAgent achieves 42.02%--44.63% recall for goal-reaching components and recovers up to 4.4 times as many correct goal-reaching dependency edges as Codex. An additional evaluation of 30 real-world PHP applications identifies 20 vulnerabilities and 13 exploit chains, nine of which achieve remote code execution (RCE).

cs.CR · cs.AI

新论文 · v1arXiv:2611.24269

Keeping Up with the Kernel: Can LLMs Adapt Linux Drivers to Interface Changes?

Xinrui Yang, Jiawen Liu, Arina Kharlamova, Humaid Alqasimi, Tianyi Zhang, Alnoor Ismail, Youcheng Sun, Chun Jason Xue

原文摘要

We analyze collateral evolution in Linux, the coordinated updates that drivers require when the kernel interfaces they depend on change, over the 20 years since it was first studied, covering releases from v3.0 to v7.2. Since v2.6.13, the number of driver files and support libraries has grown about eightfold, a single change to the most widely used library can now reach about 5.3k driver files, and such changes arrive either in bursts or spread over many releases. We introduce CoEvoBench, a benchmark that asks models to adapt an old driver module to a target kernel and evaluates the result against the developer's reference patch. The benchmark contains 316 manually confirmed tasks from 202 mainline commits and 268 modules, spanning kernel releases v6.19 to v7.2. It distinguishes 134 build-breaking tasks, where the old driver fails to compile, from 182 build-compatible tasks, where the old usage still builds. Using CoEvoAgent, we evaluate Direct, SmPL, and mini-SWE-agent with DeepSeek Flash, and compare Direct with Claude Sonnet 5.5 and GPT-6.1 Sol. With DeepSeek, default Direct generation achieves strict reference agreement on 41.0% of build-breaking tasks but only 3.3% of build-compatible tasks.

cs.SE · cs.OS

版本更新 · v2arXiv:2611.21072

Sage S2.1 Flash Technical Report

Kun Cai, Haodong Chen, Guangran Cheng, Qingxiu Cheng, Xu Dai, Guanting Dong, Qiming Ge, Lixin Gu 等 206 位作者

原文摘要

We introduce Sage S2.1 Flash, a 320-billion-parameter general-purpose mixture-of-experts model designed to reason over scientific evidence and act in interactive environments. Sage Sci-Perception uses dedicated encoders for molecular graphs and biological sequences and represents spectra as ordered patches of measurements. Modality-specific projectors map these representations into the input space of a shared backbone, which processes them alongside text and images. To develop the model's agent capabilities, we construct verifiable environments for tool use, search, and coding, as well as specialized workflows involving machine learning experiments and scientific software. Task completion is checked against execution results, changes in environment state, or submitted artifacts. We evaluate Sage S2.1 Flash on 33 benchmarks across seven domains. In the primary comparison against five baselines, it ranks first on OfficeQA Pro (72.2), MLE-bench Lite (90.3 HumanRank), Harvey LAB, and SpreadsheetBench 2, and second on OSWorld-Verified (85.2), WebArena-Verified (67.6), and DeepResearch Bench II (54.2). These results show particular strengths in using documentary evidence, producing verifiable workbooks, and carrying out machine learning tasks, alongside competitive performance in desktop and browser workflows that require the model to act on visual feedback.

cs.AI

新论文 · v1arXiv:2611.22592

Distilling World Action Models for Efficient Bimanual Manipulation via Anchored Path Matching

Jialong Liu, Junjie He, Yandu Chen, Bin Zhou, Heng Su, Peijun Tang, Jianan Wang, Changhao Chen

原文摘要

World Action Models (WAMs) jointly generate future video and robot actions through iterative denoising. Few-step distillation reduces the number of model evaluations, but its coarse updates can move the student away from the teacher's trajectory. We propose Anchored Path Matching (APM), which supervises endpoint and short-transition predictions from states reached by the student. From each state, we continue the teacher to zero noise and use its endpoint and first intermediate state as targets. Modality-routed adapters learn to match both targets from the same starting state. When the two gradients conflict, anchor-priority updates preserve the endpoint gradient and remove the opposing component of the local gradient within each modality. One checkpoint supports 1-, 2-, and 4-step joint generation. The sampling budget can be chosen at deployment without retraining or teacher queries. On RoboTwin 2.0, we train only on Clean demonstrations and evaluate directly on the domain-randomized Random setting. At one step, APM improves closed-loop success over continued base distillation at matched inference budgets by 2.0 percentage points on Clean and 1.4 on Random. Video peak signal-to-noise ratio (PSNR) rises from 30.169 to 32.317 dB, with gains in structural similarity (SSIM) and learned perceptual image patch similarity (LPIPS). On two real-robot tasks, APM improves success over the one-step teacher and reduces control-cycle latency by $21.3\times$ relative to the eight-step teacher.Project page: https://jialonglong.github.io/Anchored-Path-Matching/.

cs.CV · cs.RO

新论文 · v1arXiv:2611.22360

Can Vision-Language Models Truly Understand Images? A Benchmark Beyond Commonsense Bias

Ling Lin, Heng Su, Xiangzeng Liu, Yang Bai, Congcong Zhu, Jingrun Chen

原文摘要

Multimodal large language models (MLLMs) have achieved impressive performance on a wide range of vision-language tasks. However, it remains unclear whether their predictions are grounded in the visual content itself or are largely driven by statistical co-occurrence patterns and commonsense correlations learned from large-scale image-text corpora. Existing vision-language benchmarks predominantly consist of samples that conform to human commonsense, allowing models to achieve strong performance by exploiting dataset priors rather than genuinely understanding image content. To address this limitation, we present ContraSense, a systematically constructed benchmark for evaluating faithful vision-language understanding. ContraSense consists of carefully curated counter-intuitive image-text pairs that deliberately violate common expectations, substantially reducing the effectiveness of statistical biases and requiring models to rely on visual evidence for reasoning. We conduct comprehensive evaluations on a diverse set of representative open- and closed-source MLLMs. The results reveal a substantial performance gap between current MLLMs and humans: even the strongest closed-source model achieves only about 60\% accuracy, compared with 96.04\% for human participants. These findings demonstrate that current MLLMs still struggle with faithful visual understanding and highlight the need for more robust multimodal reasoning grounded in image content. The ContraSense benchmark is publicly available at https://huggingface.co/datasets/LingLin00/ContraSense.

cs.CV

新论文 · v1arXiv:2611.21235

Language-model agents' beliefs can be manipulated via truthful evidence in open channel

Jinwei Hu, Qisong He, Xinmiao Huang, Youcheng Sun, Yi Dong, Xiaowei Huang

原文摘要

Language-model agents' beliefs can be manipulated through open channels such as social media, even when the information they receive is truthful. When agents fill gaps between fragments with self-induced relationships, they may accept those relationships as established facts and pass the resulting rumours to others. Drawing on cognitive theory of narrative understanding and film theory of montage, we introduce Generative Montage to operationalize this failure, termed narrative overfitting, by coordinating agents to arrange truthful fragments into misleading narratives. Across 1,090 rumour targets from six Twitter events, agents often accepted rumours overconfidently, with overall acceptance exceeding 65 percent in twelve of fourteen models. Acceptance remained above 50 percent after majority voting or review of the same evidence, showing how errors can reach downstream decisions. To explain this susceptibility, fragment interventions identify posts that influence belief within complete narratives. Synthetic controls then show that similar response patterns arise from valid evidence, separating belief influence from evidential support. This distinction motivates Grounded Monitor, a proof-of-concept neuro-symbolic runtime monitor that checks direct evidential support to guide agents' judgements, improving decision accuracy by 5.6 to 29.0 percentage points across original and anonymized settings. These findings expose a cognitive route to rumour amplification and support monitoring inferred relationships before agent-generated conclusions guide public decisions.

cs.AI · cs.CL · cs.MA · cs.SI

版本更新 · v2arXiv:2511.15245

The Walls Have Ears: Unveiling Cross-Chain Sandwich Attacks in DeFi

Chuanlei Li, Zhicheng Sun, Jing Xin Yuu, Xuechao Wang

原文摘要

Cross-chain interoperability is a core component of modern blockchain infrastructure, enabling seamless asset transfers and composable applications across multiple blockchain ecosystems. However, the transparency of cross-chain messages can inadvertently expose sensitive transaction information, creating opportunities for adversaries to exploit value through manipulation or front-running strategies. In this work, we investigate cross-chain sandwich attacks targeting liquidity pool-based cross-chain bridge protocols. We uncover a critical vulnerability where attackers can exploit events emitted on the source chain to learn transaction details on the destination chain before they appear in the destination chain mempool. This information advantage allows attackers to strategically place front-running and back-running transactions, ensuring that their front-running transactions always precede those of existing MEV bots monitoring the mempool of the destination chain. Moreover, current sandwich-attack defenses are ineffective against this new cross-chain variant. To quantify this threat, we conduct an empirical study using cross-chain transaction data from the Symbiosis protocol (November 21, 2022 to April 4, 2026) and Debridge (December 21, 2022 to April 4, 2026), along with a tailored heuristic detection model. Our analysis indicates that this attack has indeed had a significant impact on DeFi.

cs.CE

版本更新 · v2arXiv:2502.20658

Curating Safe Spaces for Emotion Disclosure during Illness Recovery on Video-Sharing Platforms

Jiaying "Lizzy" Liu, Yunlong Wang, Allen Jue, Yao Lyu, Yiheng Su, Shuo Niu, Nathan TeBlunthuis, Yan Zhang

原文摘要

The advent of video-sharing platforms has transformed self-expression, transcending entertainment to encompass sensitive disclosures and emotional revelations. In this submission, we discuss our study on emotional disclosure by individuals with Schizophrenia through YouTube vlogs and its implications for designing safe online spaces.

cs.HC · cs.CY · cs.SI

版本更新 · v2arXiv:2607.21118

The Second LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results

Xiang Chen, Hao Li, Jiangxin Dong, Jinshan Pan, Xin Li, Hongbo Ding, Junpeng Jiang, Xingyu Qiu 等 92 位作者

原文摘要

This paper presents a review of the second LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aims to advance unified image restoration under diverse real-world degradation conditions, including blur, low-light, haze, rain, and snow. It provides a common benchmark for evaluating the restoration accuracy, robustness, and generalization capability of models across multiple degradation categories within a unified framework. The competition attracted 158 registered participants, and 20 teams were included in the final ranking after their submitted results were successfully reproduced and verified. This report provides a comprehensive analysis of the submitted solutions and corresponding results, highlighting recent advances in real-world all-in-one image restoration. The summarized methods and empirical findings reveal effective design strategies and establish an updated benchmark for future research in real-world low-level vision.

cs.CV

新论文 · v1arXiv:2611.17331

TTB:面向仅解码器视角合成模型高效渲染的测试时烘焙

TTB: Test-time Baking for Efficient Rendering of Decoder-only View Synthesis Models

Chin-Yang Lin, Ryo Hachiuma, Jaesung Choe, Min-Hung Chen, Yu-Chiang Frank Wang, Yen-Yu Lin, Wei-Chen Chiu, Yu-Lun Liu 等 9 位作者

AI 速读 基于摘要

提出测试时烘焙(TTB),将跨视角注意力中的全局场景信息学习并烘焙进轻量MLP,以提升仅解码器视角合成模型的渲染速度与质量。

cs.CV

查看原文摘要

Decoder-only Large View Synthesis Models (LVSMs) with KV-cache have recently achieved state-of-the-art quality by regressing novel views from neural networks without reconstructing 3D geometry, while Test-Time Training (TTT) layers save computation but sacrifice quality. We propose Test-Time Baking (TTB), a strategy that learns to bake global scene information from cross-view attention into a lightweight MLP, enabling fast and high-fidelity novel-view decoding. The first key is to repurpose the fast-weight MLP of TTT to learn the cross-view attention mapping explicitly from its input-output pairs, rather than replacing attention entirely, achieving the same rendering efficiency as TTT while delivering substantially higher quality. The second key addresses a modality misalignment between context prefilling and novel-view rendering: we disentangle context tokens into camera-only context rendering tokens to serve as TTB input, and context ground-truth tokens with image content to serve as the TTB mapping target, ensuring the baked MLPs are relieved of the modality generalization challenge between context and novel-view processing. Our method achieves up to **23x** rendering speedup with quality on par with the state-of-the-art across several benchmarks. Project page: https://test-time-baking.github.io

新论文 · v1arXiv:2611.15834

Where to Generate Touch: Do Image Latents Preserve Material Recognition?

Wanghao Ye, Aarosh Das, Sihan Chen, Yiting Wang, Bowei Tian, Guoheng Sun, Shwai He, Zheyu Shen 等 29 位作者

原文摘要

Generated touch could extend robot learning beyond recorded contacts. A tactile generator needs a latent space, and we choose one by testing whether a material classifier trained on real GelSight presses still works on encode-decode reconstructions from pretrained image models. On ObjectFolder Real, the classifier loses 6.5 to 9.7 points on reconstructions from three 16x discrete tokenizers and 0.3 points on those from the Stable Diffusion VAE (SD-VAE). The 16x tokenizers again lose far more on Touch and Go and on DIGIT object recognition (YCB-Slide). Retraining the classifier on reconstructions, with no new labels, narrows the discrete gap. SD-VAE reconstructions also keep object identity, with 76.7% object-matching accuracy against 78.9% for real touch and 67.0% for MAGVIT-v2. We therefore select SD-VAE latents and show a photo-to-touch generator trained in them. Code will be released upon acceptance.

cs.CV · cs.RO

版本更新 · v2arXiv:2611.13287

Project Progress Desk: Know Where All Your Claude Code and Codex Projects Stand at a Glance

Wanghao Ye, Yiting Wang, Shwai He, Guoheng Sun, Ziyao Wang, Yexiao He, Zheyu Shen, Zhaoyi Liu 等 25 位作者

原文摘要

Agentic coding tools such as Codex and Claude Code let developers work on many projects in parallel, but keeping track of them still means switching between chats, terminal sessions and providers. We present Project Progress Desk, a local desktop interface that brings overall progress, blockers and pending decisions into one view. Users can see which projects need attention and what remains, and compare earlier approaches before choosing how to continue. Agents report each result in a short receipt; the Desk checks it against the project's checklist and moves the bar, showing earlier estimates in a lighter shade. We describe daily use across 36 projects, including a choice between two implementations based on their recorded outcomes. At the demo, attendees will explore 30 simulated projects, trace completed work to overall progress, and watch a coding agent's new result update the overview.

cs.HC · cs.SE

版本更新 · v5arXiv:2602.23872

Altitude-Adaptive UAV-to-Map Image Matching for Aerial Geo-Localization

Xingyu Shao, Mengfan He, Liangzheng Sun, Chunyu Li, Ziyang Meng

原文摘要

Matching downward-looking unmanned aerial vehicle (UAV) images to georeferenced satellite or aerial map tiles supports map-based geo-localization when direct positioning signals are degraded or unavailable. Variations in UAV altitude change the observed ground footprint and create a scale mismatch between query images and fixed-scale map references. We address this problem with an altitude-adaptive aerial geo-localization framework. The framework estimates relative altitude from a single image using a frequency-domain representation and regression-as-classification. The predicted altitude-class center defines a scale prior that guides query normalization toward the canonical map scale before full-gallery visual place recognition. A footprint-adaptive margin classifier (FAMC) adjusts training margins according to footprint overlap. Experiments on two synthetic and two real-flight datasets show that, at the 100 m localization threshold, altitude adaptation improves average R@1 and R@5 by 50.68 and 47.20 percentage points, respectively, for our visual place recognition module compared with the same retrieval pipeline without altitude normalization. These results show that a relative-altitude-derived scale prior improves cross-altitude UAV-to-map image matching in the evaluated regions and camera settings.

cs.CV · cs.RO

版本更新 · v2arXiv:2610.18272

JevGPT: Thinking Fast and Slow in Autonomous Research

Yasheng Sun, Yanning Dai, Yimeng Chen, Nanbo Li, Firas Laakom, Yifan Xu, Piotr Piękos, Mateusz Ostaszewski 等 12 位作者

原文摘要

Autonomous research agents must acquire and reason over evidence within a limited budget. Yet relevant sources can remain uninspected or unused, leaving a gap between retrieval coverage and the evidence that informs research. The challenge is to align fast local judgments with changing evidence needs and feed their findings back into research decisions. We introduce JevGPT, a dual-system architecture for autonomous research that couples fast evidence processing with deliberative research planning. System Two sets evidence objectives and integrates findings, while System One locates support, assesses relevance, and guides further inspection. Independent source judgments run in parallel; selected original passages inform the next research step. Experiments on fixed-corpus question answering and document ranking show that JevGPT achieves leading task performance, with faster completion and lower cost than comparably effective research agents. Evidence analysis shows broader source inspection and greater coverage of supporting documents in the research loop, highlighting efficient evidence processing as a route to more capable autonomous research.

cs.CL · cs.AI · cs.IR

新论文 · v1arXiv:2611.10510

ReSkill: Selective Self-Improvement for Robot Manipulation

Zheng Sun, Zhihao Li, Zhuo Li, Wenrui Liu, Xin Wang, Fei Chen

原文摘要

Self-improvement on compositional manipulation tasks requires deciding what to reuse, where to improve, and which changes to retain. We present ReSkill, a selective self-improvement framework that concentrates revision on capability gaps. A coding agent constructs an object-centric task graph from an instruction and a skill library, then uses node-level execution records to locate failures. At the task level, it revises stage organization, hand-off conditions, and recovery routes; at the skill level, it strengthens perception, motion, manipulation, and verification capabilities that repeatedly fail. Candidate revisions undergo full-task evaluation and paired comparisons before adoption, allowing local changes to accumulate into validated skills and an independently executable policy. The agent participates only during development; the deployed policy calls the retained skills without invoking the agent at run time. On the same development set, average success across ten RoboDojo tasks rises from 30.0% for the initial versions to 86.2% for the final adopted programs; retained programs achieve 83.6% in recorded robustness and model-selection evaluations. Across eight real-world tasks, ReSkill succeeds in 72 of 80 rebuilt-simulation trials and 62 of 80 real-robot trials (77.5%). The median revision changes only three functions, approximately 0.5% of a program, while 39% of task-specific functions in later-added tasks directly reuse existing implementations. These results show how locating local deficiencies, validating candidate changes, and accumulating reusable skills can improve execution of compositional manipulation tasks.

cs.RO

新论文 · v1arXiv:2611.08412

AI4Math 淘金热 II:AI 辅助证明有哪些特征?

The Gold Rush in AI4Math, II: What are signatures of AI-assisted Proofs?

Yuanchuan Guo, Jiashun Jin, Zheng Tracy Ke, Bingcheng Sui

AI 速读 基于摘要

作者构建配对论文队列并提出 ProofTrace 框架,用证明支持图的可解释特征刻画 AI 参与数学证明的痕迹,并检验其检测效果。

cs.AI · stat.AP

查看原文摘要

The growing use of AI in mathematics raises a question: can we detect AI involvement in proofs, separately from AI assistance with writing? Historical arXiv papers, recent papers disclosing substantive AI use, and manuscripts released by OpenAI provide a rich empirical basis for studying this question. However, several challenges remain: lack of matched case-control pairs; potential incompleteness of disclosure; and lack of ready-to-use features designed to capture signals of AI involvement in proofs. To address these challenges, we construct five cohorts comprising 8,281 papers by combining existing manuscripts with those we produced using generative AI. These cohorts span different levels of AI involvement and include matched pairs of papers addressing the same research problems. We then introduce ProofTrace, a framework that represents each paper as a graph of immediate proof support (GIPS) and extracts interpretable features of mathematical organization. Our study yields three discoveries. First, principal-component projections of our features reveal a qualitative gradient of AI involvement, where AI-reworded papers remain close to human papers, the two AI-generated cohorts depart in broadly shared directions, and papers disclosing substantive AI use occupy intermediate positions which shifts toward AI-generated cohorts over time. Second, we identify recurring signatures of AI-generated proofs, such as fewer externally cited results, greater reliance on intermediate conclusions, and altered graph connectivity; many of these signatures persist under controls for research field, manuscript length, or graph size. Finally, in a separate detection experiment, ProofTrace distinguishes human-written papers from those disclosing substantive AI use. Its performance remains stable under AI rewording, whereas the performance of state-of-the-art text-based detectors declines sharply.

新论文 · v1arXiv:2611.07853

CANMentor: A Large-Small Model Collaboration Framework for CAN Bus Intrusion Detection

Zhiquan Liu, Haolin Gao, Bo Wu, Jingjing Guo, Heng Sun, Jianfeng Ma

原文摘要

The Controller Area Network (CAN) bus lacks built-in security mechanisms, making real-time intrusion detection necessary. However, resource and latency constraints limit vehicle-side intrusion detection systems (IDSs) to lightweight models, whose detection performance and generalization can degrade under non-independent and identically distributed (non-IID) data. Meanwhile, uploading original CAN messages to the cloud for more powerful model inference risks exposing sensitive vehicle information. We propose CANMentor, a large-small model collaboration framework in which a cloud-side large language model (LLM) teacher supervises vehicle-side lightweight IDS models for CAN bus intrusion detection. Each vehicle first performs local inference, and a privacy-aware generator then produces proxies from the original CAN messages for cloud-side teacher inference to protect data privacy. The vehicle uses the teacher prediction only when the response arrives within a prescribed latency bound and otherwise retains the local prediction; all returned teacher logits are converted into soft targets for periodic knowledge distillation. On non-IID partitions of the ROAD dataset and the HCRL Car-Hacking dataset, knowledge distillation yields maximum relative Macro F1 improvements of 25.01% and 20.79%, respectively. Teacher predictions also improve detection accuracy for CAN messages near the local decision boundary by 38.71-42.00 percentage points.

cs.CR

新论文 · v1arXiv:2611.06069

SynMOE: A Syntax-Aware MOE-Guided Approach for PEFT-Based Code Intelligence Learning

Shuo Liu, Hao Ning, Jacky Keung, Zhen Yang, Xiao Yu, Xing Hu, Yicheng Sun

原文摘要

Parameter-Efficient Fine-Tuning (PEFT) has emerged as an important approach for adapting Language Models (LMs) in downstream tasks. However, in the domain of code intelligence, the performance of most PEFT methods relatively drops compared to Full fine-Tuning (FT), hindering their broader applicability. One of the main reasons is that current PEFT methods are generally based on assumptions about the low-rank nature or sparsity of parameter updates, lacking explicit modeling of code-related information. To tackle this limitation, we propose SynMOE, a syntax-aware MOE-guided approach for PEFT on code intelligence learning. Specifically, SynMOE contains two stages: syntactic information extraction and syntax-aware MOE-guided adaptation. It first obtains the syntactic labels of source code from Abstract Syntax Trees (ASTs), and then aligns the labels with the input tokens of code LMs. In the second stage, syntactic labels are integrated into the MOE module, participating in the routing decision of MOE for a more powerful syntactic-aware token representation. We evaluate the effectiveness of the proposed approach by applying it to two typical PEFT methods, LoRA and $(IA)^3$, across three diverse code intelligence tasks. Experimental results show that SynMOE achieves consistent and significant improvements. Even compared to FT, SynMOE achieves comparable or superior performance while being more computationally efficient. In addition, we also conduct ablation studies, hyperparameter analysis, and evaluation in the low-resource scenario to provide a comprehensive investigation of the proposed approach.

cs.SE

版本更新 · v2arXiv:2610.30218

JANUS: Agentic Cross-Language Fuzzing Harness Generation for Android Native Libraries

Xiangyu Zhang, Yucheng Su, Lingling Fan, Yinan Li, Sen Chen

原文摘要

Modern Android apps extensively rely on native libraries, bridging Java/Kotlin and C/C++ through the Java Native Interface (JNI). This cross-language interoperation, however, exposes the memory-safe Android Runtime to the unsafe C/C++ world, creating an attack surface that has been repeatedly exploited for full device compromise. While fuzzing is a proven technique for vetting native libraries, state-of-the-art harness generation tools struggle to faithfully capture closed-source cross-language API usage: (i) precise program analysis across the JNI boundary does not scale, whereas lightweight approximations miss critical invocation patterns; and (ii) none tackles the construction of complex composite objects consumed by JNI methods. In this paper, we propose JANUS, the first agentic approach to synthesizing cross-language JNI-aware fuzzing harnesses for Android native libraries. JANUS iteratively resolves both explicit and implicit cross-language call dependencies to recover app-specific runtime context, and recursively assembles cross-language argument objects in a bottom-up manner. JANUS leverages an autonomous agentic workflow to reduce reliance on hand-crafted heuristics, capturing the vast landscape of hidden API usage knowledge embedded in closed-source native libraries. Evaluation on 44 popular real-world apps (such as Google and YouTube Music, covering 21,386 JNI methods total) shows that JANUS produces over 5.9 times as many valid harnesses (6,094) as state-of-the-art automatic harnessing tools. On pre-installed apps from five mainstream Android vendors (e.g., Xiaomi, Vivo, Samsung), JANUS further uncovers 6 previously unknown vulnerabilities in closed-source native libraries.

cs.SE · cs.CR

新论文 · v1arXiv:2611.01954

Towards Self-Evolving Narrative Systems: Real-Time Adaptation and Long-Term Optimization with LLMs

Ruisheng Sun, Jiaqi Shao, Weijia Han, Linxi Ju, Yunzhen Zhang, Binyan Sun, Rong Chen, Benjamin Blas Maristany 等 12 位作者

原文摘要

Traditional interactive narrative systems offer strong authorial control and structural coherence but often restrict player agency. In contrast, LLM-driven narratives enable open-ended generation and greater flexibility, yet frequently suffer from inconsistency and diminished narrative control. To navigate this trade-off, we propose a hybrid narrative framework that dynamically balances pre-authored content with real-time LLM generation via semantic similarity alignment. Additionally, sustaining narrative quality over extended gameplay remains a core challenge in LLM-based storytelling. To address this, we introduce a self-evolving, feedback-driven optimization framework that leverages in-context learning to iteratively refine prompts, eliminating the need for manual prompt engineering. Through a case study and participant-based evaluation, we show that our framework enhances narrative coherence while preserving player agency, effectively aligning generated content with both authorial intent and evolving player behavior.

cs.CL

新论文 · v1arXiv:2610.39505

Agent-Wise Test-Time Normalization for Camera-Based Cooperative Perception with Corrupted Collaborators

Yu Wang, Shaohua Wang, Yicheng Li, Kecheng Sun

原文摘要

Intermediate-fusion cooperative perception lets a vehicle detect objects beyond its own field of view by fusing features shared by nearby agents. When only a collaborator's cameras are degraded by fog, motion blur or exposure errors, the features it shares drift away from the training distribution while the ego input stays clean, and cooperation can become worse than not cooperating at all. Test-time batch-normalization adaptation, the standard training-free remedy, estimates statistics over the pooled batch of all agents and therefore normalizes both the clean ego and the corrupted collaborator with a mixture of two distributions. We show that this mixing harms even the clean ego: when the ego shares BN statistics with a corrupted collaborator, its detection from its own features drops by 3.58 to 6.68 AP@0.5 points although its cameras are untouched. We propose AgentNorm, an agent-wise test-time normalization that i) estimates the normalization statistics of every collaborator from its own current observation and ii) anchors the ego to its source statistics, so that the ego path remains exactly the original model. AgentNorm has no learnable parameters, needs no gradients or labels, is independent of the order of test frames, and runs locally on each agent without changing the transmitted features. On camera-based OPV2V with four fusion checkpoints and collaborator-only corruptions, AgentNorm raises AP@0.5 under severity-5 fog from 29.42-37.25 to 43.32-58.86 and outperforms pooled normalization by 5.53-12.94 points under fog and motion blur, at an extra latency of 2.3 ms per frame. On the real-world DAIR-V2X-C dataset, it outperforms pooled normalization in all ten infrastructure-corruption settings. We also report the cases it does not fix: occlusion, which removes image content rather than shifting feature statistics, and the case in which all agents share the same shift.

cs.CV · cs.AI

新论文 · v1arXiv:2610.37833

Depth through Recurrence: Towards Ultra-Efficient On-Device ASR

Chen Feng, Tianyi Xu, Ramchalam Kinattinkara Ramakrishnan, Yicheng Lin, Shaojie Zhuo, Zhaocong Yuan, Chenzheng Su, Xiaopeng Zhang

原文摘要

Modern automatic speech recognition (ASR) systems have achieved remarkable accuracy by scaling model depth and capacity, but at the cost of increased memory, energy, and computational demands. On edge devices where ASR is often most needed, such as watches and glasses, deploying such large models is infeasible due to extremely constrained resources. This raises a fundamental question: can we achieve high representational power in deep ASR models without scaling up parameterization? In this work, we revisit the role of depth and identify layer wise representational dynamics, in which most layers learn functionally similar transformations. Motivated by this insight, we propose a block-recurrent ASR architecture that replaces parameterized depth with a small set of recurrent blocks, each consisting of weight-shared layers, thereby preserving effective depth while drastically reducing model size. Through representation-guided grouping and knowledge distillation, block-recurrent models retain the accuracy of large reference models while using an order of magnitude fewer parameters. Across Open ASR Leaderboard benchmarks, a model with only two shared blocks recovers 97.4% of the accuracy of large models on average. The compact backbone further enables efficient on-device personalization through lightweight MoE-LoRA adaptation, allowing user-specific models to match or surpass the accuracy of general-purpose ASR systems with significantly lower inference cost. By reusing weights across recurrent steps, the proposed architecture reduces memory-access overhead and inference energy consumption. Together, these results show that high quality ASR can be achieved without large parameterization, and that structured recurrence provides a principled path towards ultra-compressed, energy-efficient, and personalized speech recognition on the edge.

cs.LG

版本更新 · v2arXiv:2603.15401

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?

Tingxu Han, Yi Zhang, Wei Song, Chunrong Fang, Zhenyu Chen, Youcheng Sun, Lijie Hu

原文摘要

Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear, and no standard procedure tests an individual skill before installation. We present swe-skills-bench, a skill-centric, requirement-driven benchmark that measures how much individual agent skills improve performance on real-world software engineering (SWE) tasks. We start from 98 public SWE skills, each paired with a real GitHub repository pinned at a fixed commit. For each skill, we derive repository-specific requirements, create executable verifiers, and build a reproducible environment. Under each of four agent-model configurations, we run every task once without the skill and once with it, yielding 3,920 paired evaluations. For each requirement, we compute a paired delta, i.e., the change in outcome when the skill is added. We then aggregate these deltas across a skill's ten requirements into a per-skill utility profile, and use a statistical test to classify each skill as Golden (significantly helpful), Ineffective (no significant effect), or Harmful (significantly detrimental). Our results show that skills provide limited benefits: 92 of 98 skills have no statistically significant effect, and adding skills raises the average pass ratio only from 76.6% to 76.9%. The few helpful skills supply procedures that the agent would otherwise omit (gains of up to $+17.7$ points). In contrast, harmful skills anchor the agent on their own templates and override the task's explicit instructions (losses of up to -17.0 points). Our code is available at https://github.com/ControllableModel/SWE-Skills-Bench.

cs.SE · cs.AI

新论文 · v1arXiv:2610.36767

Can LLMs Reliably Grade Olympiad Proofs? A Study of Mathematical Verification with LLMs

Azim Ospanov, Zijin Feng, Ding Ding, Chengwu Liu, Haoli Bai, Jiacheng Sun, Lifeng Shang, Farzan Farnia

原文摘要

Large Language Models (LLMs) have made remarkable progress on solving competition-level mathematics, yet their ability to verify natural-language mathematical proofs remains relatively underexplored. This gap is especially pronounced for Olympiad-level proofs, which require meticulous assessment of each claim in a long reasoning chain. Current proof verification thus primarily relies on expert inspection, which is costly to scale. In this paper, we present a systematic study of LLM-based verification in this setting. Specifically, we introduce a human-curated dataset of USAMO 2025 candidate solutions with expert grading, and conduct a broad evaluation of existing LLM verifiers across frontier models. We also propose TROJAN, an iterative self-critique pipeline for generating high-fidelity adversarial proofs at scale. Our comprehensive evaluation covers 20 models spanning seven metrics, two prompt styles, three inference methods, and three prompt templates, showing that state-of-the-art models still leave considerable room for improvement. To narrow this gap, we propose MABGrader, a Multi-Armed Bandit framework that reframes grading as arm selection over the discrete score space. MABGrader outperforms the SOTA ProofGrader by 26.4% in Quadratic Weighted Kappa and reduces grading error by 14%. Code and dataset are available at https://github.com/aziksh-ospanov/TROJAN.

cs.AI

新论文 · v1arXiv:2610.36621

Noise Shapes the Surplus: Strategic Play Against No-Regret Learners

Yiheng Su, Emmanouil-Vasileios Vlatakis-Gkaragkounis

原文摘要

Recent work has shown that, in zero-sum games, an optimizer can extract $Ω(\sqrt{T})$ strategic surplus---cumulative payoff above the minimax benchmark---against noiseless no-regret learners with a constant step size. However, in practice, learners often act on perturbed payoff scores and use decaying learning rates $η_t$. Since existing extraction mechanisms rely on exact scores, a natural question is whether noise shields the learner from exploitation and eliminates surplus altogether. We address this question for the widely used class of Follow-the-Regularized-Leader (FTRL) algorithms. Under standard regularity conditions, we establish three results, none of which assumes independence of the noise. First, under summability conditions, passive play of a strategy fixed independently of the horizon earns at most constant surplus. Second, we design a new mechanism that exploits the learner's noise-dependent response: a clairvoyant optimizer who knows the update rule and the limiting mean response secures $Ω(1/η_T)$ surplus whenever that mean is profitable. Third, even when that mean is not profitable, active alternating play extracts $Ω(\sum_{t<T}η_t)$ surplus by exploiting the learner's movement rather than its location, under suitable responsiveness and stability conditions. Finally, at the canonical learning rate $η_t\propto t^{-1/2}$, we recover the noiseless $Ω(\sqrt{T})$ rate for mean-zero, finite-variance perturbations---whether fresh with arbitrary temporal dependence or accumulated from i.i.d. increments---provided the limiting mean response is profitable.

cs.GT

版本更新 · v2arXiv:2609.34717

ReMCTS: Reflection-Enhanced Monte Carlo Tree Search for Code Generation

Huifei Wang, Xinying Huang, Yiheng Sun, Yifan Yuan

原文摘要

Open-weight large language models (LLMs) can generate function-level programs from natural-language prompts, but plausible candidates still fail on hidden semantics and repeat mistakes across repair attempts. We present ReMCTS, an execution-grounded, memory-augmented, LLM-guided MCTS-style search framework. It organizes program candidates as tree states, retains branch-local debugging context, retrieves failure experience across branches, and distinguishes failed checks from unavailable evidence. On HumanEval and MBPP-Sanitized, visible-test ReMCTS improves over direct generation in 8 of 10 model-dataset pairs under held-out evaluation, whereas proxy-only search is less stable. Controlled tree-search, sampling, repair, and memory ablations characterize the source and limits of these gains. A 30-task HumanEval-X C++ pilot further demonstrates compatibility with compiler-backed execution, but does not constitute a broad multilingual evaluation.

cs.CL

新论文 · v1arXiv:2610.36261

The Complexity of Strategizing Against No-Regret Learners: Pure When It Is Easy, Hard Even When Mixed

Yiheng Su, Emmanouil-Vasileios Vlatakis-Gkaragkounis

原文摘要

We study the computational complexity of clairvoyant strategy optimization against a known online learner in finite-horizon repeated games. In general-sum games with bounded payoffs, unless $\mathsf{P}=\mathsf{NP}$, no polynomial-time optimizer can achieve a reward within $cT$ of the reward of the optimal pure-action sequence for an absolute constant $c>0$, even when allowed to output explicitly represented mixed strategies at every round. Our hardness result strengthens prior work along two complementary axes: it extends to a broader class of learning dynamics, including widely used mean-based algorithms, answering an open question of Assos, Dagan, and Rajaraman (2025) for learners beyond multiplicative weights; and it permits mixed outputs while retaining the weaker pure-sequence benchmark. Thus, neither mixed strategies nor algorithmic specificity removes the computational obstruction in general-sum games. In sharp contrast, zero-sum games exhibit the reverse phenomenon: deterministic pure actions suffice for efficiently recovering the leading surplus guarantees previously obtained through mixed play against Follow-the-Regularized-Leader (FTRL) opponents. Thus, the two regimes form a striking mirror image: mixed play cannot overcome general-sum hardness even against a pure benchmark, whereas pure play retains the full surplus guarantees of mixed strategies in zero-sum games.

cs.GT

版本更新 · v2arXiv:2605.17912

WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform

Zhuohang Li, Yiding Ma, Yu Shang, Lei Jin, Shengyuan Wang, Jianjie Fang, Zhaolu Wang, Xvyuan Liu 等 29 位作者

原文摘要

World models have emerged as a central paradigm for embodied intelligence, enabling agents to predict action-conditioned future and reason about environmental dynamics. However, existing embodied world model benchmarks are still largely confined to vision-only prediction, offline embodied applications, and simulator-based evaluation, making them insufficient for assessing increasingly comprehensive world models. In this work, we introduce WorldArena 2.0, an expanded benchmark that systematically broadens embodied world model evaluation along three dimensions: modality, functionality, and platform. Along the modality dimension, WorldArena 2.0 extends evaluation from vision-only to visuotactile modalities, enabling assessment of multimodal perception and prediction. Along the functionality dimension, it extends beyond policy evaluation and planning to assess world models as interactive RL environments for policy optimization. Along the platform dimension, it moves beyond simulator-only evaluation to a diverse suite of simulated and real-world robotic settings across multiple embodiments. Under a standardized protocol, WorldArena 2.0 comprehensively evaluates perceptual quality, interactive utility, and cross-platform performance, providing a comprehensive testbed for tracking progress toward embodied world models. The project page including codes and demos is available at: https://world-arena.ai/.

cs.RO · cs.CV

版本更新 · v4arXiv:2609.31494Google Research

面向可证明隐私的联邦数据学习

Toward provably private learning from federated data

Katharine Daly, Yu Xiao, Zachary Garrett, Brett McLarnon, Jianpeng Hou, Arun Ganesh, Yanxiang Zhang, Noriyuki Takahashi 等 12 位作者

AI 速读 基于摘要

提出基于可信执行环境(TEE)的下一代联邦学习系统,首次提供可外部验证的中心化差分隐私(DP)保证,并改善隐私-效用权衡。

cs.CR

查看原文摘要

Federated Learning (FL) allows devices with private data to collaborate in training a shared model. We present a next-generation FL system based on Trusted Execution Environments (TEEs) that addresses operational challenges associated with earlier systems and provides externally verifiable central Differential Privacy (DP) guarantees for the first time while offering a better privacy-utility tradeoff. In our system, devices upload data encrypted with keys managed by a TEE-hosted Key Management Service (KMS). The uploaded data is cryptographically tied to a policy limiting the set of Python programs that may later process the data in server-side TEEs. External parties may inspect public transparency logs to observe the set of workloads allowed by these policies. Our experimental results show that the new system improves device coverage and favorably shifts privacy-utility curves by enabling collected data to be integrated into the server-side workload at a schedule that optimizes DP guarantees and is unaffected by device availability. Our new system has been productionized, enabling models for the Android Keyboard (Gboard) to be trained faster and achieve better accuracy under smaller, now externally verifiable privacy budgets in comparison to models trained using the prior system.