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

+1680新增论文
+1333其中 AI 相关
+187已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-17 23:35各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 08:02 — 2026-11-18 08:02(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:2026-11-18 04:28最近发现新增版本:2026-11-17 23:35库内论文最新更新时间:2026-11-17 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。

25,786 已收录论文21,491 AI 相关7,725 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 19 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v2arXiv:2604.17277

Analog Resonant Recurrent Neural Networks via Metacircuits

Zixin Zhou, Tianxi Jiang, Menglong Yang, Mengli Sui, Yizhuo Zhang, Zhihua Feng, Qingbo He, Shiwu Zhang

原文摘要

Physical neural networks offer a promising route to fast and energy-efficient edge intelligence by embedding computation in the intrinsic dynamics of materials and devices. However, processing temporal signals requires recurrent networks with memory, whose trained dynamics are hard to reproduce faithfully in physical systems. Here we present an analog resonant recurrent neural network (R$^2$NN) implemented as a metacircuit of coupled local resonators. A reformulated mechanical-electrical analogy based on frequency-dependent negative resistances maps a trained network one-to-one onto the metacircuit, with every trainable parameter realized as a resistance. Training tunes local resonances and global resistive couplings so that past responses persist as recurrent memory and interfere with incoming inputs, and the resulting impedance landscape routes different frequencies to distinct outputs. Exploiting this recurrent memory, the metacircuit solves a temporal-parity task whose output depends on the entire input history. Building on the learned frequency selectivity, stand-alone R$^2$NN systems classify raw tactile, acoustic and vibration signals in real time and directly drive downstream hardware. This work establishes engineered locally resonant dynamics as a physical substrate for recurrent neural computation and opens a route to compact, low-latency neural hardware for machine intelligence at the edge.

cs.LG · cs.AI · cs.ET · physics.app-ph

版本更新 · v2arXiv:2607.24984

Automatic Knowledge Graph Construction and Query for Earthquake Catalogs

Yuxin Zhou, Huai Zhang, S. Mostafa Mousavi

原文摘要

In recent years, the number of events in earthquake catalogs has significantly increased due to the utilization of more effective deep learning based detectors and phase pickers but answering open ended questions such as what characterizes this sequence? remains constrained by rigid spatiotemporal windowing and subjective expert interpretation. We present the first systematic application of graph based retrieval augmented generation GraphRAG directly to raw, tabular catalog records across three independently featured catalogs, a reservoir adjacent swarm, the 2019 Ridgecrest tectonic sequence, and the 2021 Maduo Mw7.4 aftershock sequence. Without the need for manual data structuring, the pipeline builds structurally complete, queryable knowledge graphs for all three. Rigorous evaluation individually verified against catalog derived ground truth and a rule based reference graph exposes failure modes, and four seismology informed prompt fixes eliminate all targeted fabrications while sharply improving mechanism reasoning. A vector RAG baseline demonstrates the graph layers distinctive value, catalog wide summarization and temporal stage comparison. In addition, we have identified two main pitfalls that need attention. GraphRAG thus offers a practical, transferable, near zero cost query interface for earthquake catalogs, where careful prompting ensures the results are consistently accurate and trustworthy.

physics.geo-ph · cs.AI · cs.LG

新论文 · v1arXiv:2611.15105

VecDBLens: An Evaluatology-Based Framework for Vector Database Diagnosis

Yutong Zhou, Guoxin Kang, Wenxin Zhou, Haoyu He, Yuedong Zhu, Lei Wang, Wanling Gao, Fanda Fan 等 9 位作者

原文摘要

Vector databases are increasingly deployed as retrieval pipelines in which representation, indexing, and query-time execution jointly determine accuracy, throughput, and cost. Existing vector database evaluations primarily focus on indexing while treating embeddings as fixed inputs and ignoring the role of query-time execution, making it difficult to decide whether a bottleneck should be addressed by changing the embedding model, the index, or the query-processing functions. To address the above limitation, we introduce VecDBLens, an Evaluatology-based framework that treats the function under diagnosis as an evaluated object and all remaining dataset, workload, parameter, and runtime factors as matched evaluation conditions. VecDBLens attributes performance differences to individual evaluated objects through comparisons under matched evaluation conditions, summarizing their performance and stability across multiple datasets and workloads. It further analyzes interactions among objects using analysis of variance (ANOVA), thereby turning vector database benchmarking from leaderboard ranking into a reproducible diagnostic procedure. VecDBLens reveals two key insights. First, retrieval performance is fundamentally upper-bounded by embedding quality, revealing that many apparent indexing failures are therefore representation-side limitations. Second, stronger index parameterization is not always beneficial: overly aggressive configurations can reshape neighborhood topology and cause recall regression. These results challenge the common practice of evaluating vector databases primarily through indexing and show that real-world limitations arise from constraints across retrieval functions rather than any single function alone. VecDBLens provides a principled basis for identifying the true performance drivers of vector databases and for guiding their design in practical applications.

cs.DB

新论文 · v1arXiv:2611.14811

Improved last-iterate bounds for SGD with and without replacement

Yimin Zhong, Jiaxin Zhou

原文摘要

In this work, we study last-iterate convergence bounds for stochastic gradient descent (SGD) on convex and $β$-smooth loss functions and improve the bound from $\cO((\log T)^3/T)$ to $\cO((\log T)^3/(T\log\log T))$ in the interpolation regime. The improvement comes from applying a horizon-dependent multiscale estimate of gradients to the comparison of trajectories. The bound applies to both sampling with replacement and sampling without replacement within one pass.

stat.ML · cs.LG · math.OC

版本更新 · v2arXiv:2611.05538

Recasting Visual Language Models as EEG Foundation Models for Clinical Neurodiagnostics

Xin Zhou, Elena Sergeeva, Nan Bi, Wenyu Song, Lijun Yin, Hao Deng

原文摘要

Historically automated electroencephalography (EEG) systems was done using task-specific supervised models trained on purposely annotated data. A more recent modeling paradigm relies on creating a unified representation, or a 'foundation model', for multiple modality-specific tasks through large-scale domain-specific pretraining on the unannotated EEG signal. The quality of this unified representation directly depends on the availability of the modality-specific datasets. At the same time, generalist Vision Language Models (VLMs) exhibit broad few-shot learning capacities as well as good fine-tuning adaptability to different visual and language tasks. Can VLMs learn how to read and interpret EEG visually, emulating to a degree the way human clinicians inspect the EEG patterns? In this work we make a case that they can: we show that generalist VLMs without large-scale EEG pretraining perform competitively across a collection of clinical neuro-diagnostic tasks, can adapt to different tasks in a few-shot learning setting better than specialist foundation models, and exhibit better performance with model scaling when modality-specific models fail to exhibit.

cs.LG

版本更新 · v4arXiv:2512.02581

Generative Online Reinforcement Learning

Chubin Zhang, Zhenglin Wan, Feng Chen, Fuchao Yang, Lang Feng, Yaxin Zhou, Xingrui Yu, Yang You 等 10 位作者

原文摘要

Reinforcement learning (RL) faces a persistent tension: policies that are stable to optimize (e.g., Gaussians) are often too simple to represent the multimodal action distributions required for complex control. Conversely, expressive generative policies---such as diffusion and flow matching---can be difficult to optimize in online RL due to intractable likelihoods and gradients propagating through long sampling chains. We address this tension with a key structural principle: decoupling optimization from generation. Building on this, we introduce GoRL (Generative Online Reinforcement Learning), an algorithm-agnostic framework that trains expressive policies from scratch by confining policy optimization to a tractable latent space while delegating action synthesis to a conditional generative decoder. Using a two-timescale alternating schedule and anchoring decoder refinement to a fixed prior, GoRL enables stable optimization while continuously expanding expressiveness. Empirically, GoRL consistently outperforms unimodal and generative baselines across diverse continuous-control tasks. Notably, GoRL achieves returns exceeding 870 on HopperStand, more than $3\times$ the strongest baseline; on high-dimensional humanoid tasks, it further outperforms the strongest non-GoRL baseline by over an order of magnitude. Code is available at https://github.com/bennidict23/GoRL.

cs.LG

新论文 · v1arXiv:2611.12000

HyPLM Technical Report

Haowei Lin, Cai Zhou, Xiangxin Zhou

原文摘要

Protein language models (PLMs) are standard tools for variant-effect prediction, protein annotation and design, but the compute needed to train and serve them keeps growing. We present HyPLM-Flash, an efficient and open PLM trained by Hyra 2.0, the research agent developed by our team. HyPLM-Flash is a 650-million-parameter masked language model trained on 726 billion tokens, 0.73 times the data of ESM-2 650M and a fifth to an eighth of the data of E1-600M and ESM C 600M. It runs on an inference engine with fused kernels and INT8 matrix multiplication, embedding about 130,000 residues per second on a single NVIDIA H20 GPU, 1.9 to 2.7 times faster than other 600M-class encoders. In a matched evaluation against 28 public checkpoints on 32 tasks, HyPLM-Flash reaches a ProteinGym zero-shot Spearman correlation of 0.409, statistically tied with ESM-2 650M, ESM C 600M and E1-600M, and the highest organismal-fitness score among self-supervised single-sequence models. It gives the best long-range contact precision of all models evaluated, including ESM-2 15B and ESM C 6B, and a lower masked-residue loss than ESM-2 650M, ESM C 600M and E1-600M on held-out sequences and on recently released PDB chains. Matching state-of-the-art accuracy at a fraction of the training and inference cost, HyPLM-Flash sets a new Pareto frontier for protein language models. We have released the model weights and the inference engine at https://github.com/Tencent-Hunyuan/hyra-results/tree/main.

cs.LG · q-bio.BM

新论文 · v1arXiv:2611.11997

HyInv Technical Report

Haowei Lin, Cai Zhou, Xiangxin Zhou

原文摘要

Inverse folding designs amino-acid sequences for a given protein backbone, and screening needs many candidates that are both diverse and well folded. We present HyInv, a 1.96-million-parameter backbone-conditioned graph network with an encoder-decoder architecture, trained by Hyra 2.0, the research agent developed by our team: pretrained with random-order autoregressive sequence modeling, followed by structure-reward reinforcement learning. At inference, a grouped draft-and-rewrite sampler that uses separate draft and rewrite temperatures improves refolding TM-score at matched diversity. An optimized implementation with BF16 numerics designs 128 sequences for a 402-residue backbone in 50.6 ms on a single NVIDIA H20 GPU, about 52 times faster than the reference sampler, and an exact FP32 path that returns the reference sequences is 8.7 times faster. Across five benchmark datasets and seven dataset-predictor combinations, HyInv reaches a higher average scTM than all ten external baselines at comparable or higher sequence diversity, with large margins over ProteinMPNN and ProteinZero V2. The same default setting supports de novo backbones, pocket-constrained libraries, enzyme redesign with the catalytic site kept, and loop redesign. We have released our code and model at https://github.com/Tencent-Hunyuan/Hyra-results/tree/main/AI4Science/hyinv.

cs.LG · q-bio.BM

版本更新 · v2arXiv:2610.16776

Game-Creation-Agents: Autonomous Game Production

Xiangxin Zhou, Jiaqi Tang, Ke Ma, Wenhao Yang, Jiarui Yao, Boye Niu, Haiyang Guo, Yifei Zhao 等 17 位作者

原文摘要

Game-Creation-Agents (GCA) turns a natural-language request into a runnable Phaser 4 browser game. The pipeline first builds a multimodal game design document that couples mechanics and scene contracts to grounded visual references. It then projects that document into a runtime scaffold, machine-readable contracts, and deterministic tests. Eight specialized agents next carry out production: scenes are implemented serially, assets are produced in parallel, and one reduced manifest joins the two branches into a single build. Build-linked real-UI checks and a code-blind critic then verify that build and decide whether the game may ship. Each blocker returns to the agent that owns the affected artifact for a bounded repair, and the game is released once all the gates pass. We evaluate finished games separately, through their rendered interfaces alone, over prompt-matched tasks run under a common protocol. GCA achieves stronger requirement satisfaction, core mechanics, content depth, and functional visuals than a comparable open pipeline. In a side-by-side human study, raters also score GCA's games higher on every dimension and prefer them overall.

cs.AI · cs.MA

新论文 · v1arXiv:2611.09109

DARIC: A Position-Independent KV Cache Reuse System with Distribution-Aware Recomputation

Weikang Wang, Haiyang Liu, Xin Zhou, Jun Liu, Weifeng Zhang

原文摘要

The context lengths of large language models (LLMs) are rapidly increasing in real-world applications such as agentic systems and retrieval-augmented generation (RAG). To accelerate LLM inference in these scenarios, reusing position-independent key-value (KV) caches across requests has emerged as a promising approach. This technique typically relies on recomputing a selected subset of tokens to restore cross-chunk interactions. However, existing solutions suffer from critical limitations in both algorithmic efficiency and system deployment. Algorithmically, they overlook the distribution of KV cache deviations, leading to either high token-selection overhead or degraded generation quality. At the system level, the reliance on custom LLM execution flows for recomputation complicates deployment and prevents seamless integration with highly optimized inference engines. In this paper, we propose DARIC (\textbf{D}istribution-\textbf{A}ware \textbf{R}ecomputation for \textbf{I}ndependent KV \textbf{C}ache Reuse), a novel KV cache reuse method based on system-algorithm co-design. At its core, DARIC introduces a distribution-aware token selection strategy that adaptively schedules token recomputation based on empirical KV deviation patterns, striking an optimal balance between generation quality and computational efficiency. Moreover, DARIC is built on a lightweight system architecture that enables independent KV cache generation and recomputation with minimal integration overhead, fully preserving existing system-level optimizations of standard inference engines. Comprehensive experiments across various datasets and LLMs demonstrate that DARIC consistently outperforms state-of-the-art methods, achieving a 1.1$\times$--4.5$\times$ speedup in time-to-first-token (TTFT) with negligible loss in generation quality. Code is available at https://github.com/Lenovo-ICI/DARIC.

cs.DC

新论文 · v1arXiv:2611.08095

基于高分辨率航空影像与多模态数据的瑞士全国尺度树种组成制图

National-scale mapping of tree species composition in Switzerland from high-resolution aerial imagery and multimodal data

Yixin Zhou, Luca Ferrari, Verena C. Griess, Nataliia Rehush, Konrad Schindler, Mirela Beloiu

AI 速读 基于摘要

作者利用深度学习融合航空RGB影像、ALS、卫星嵌入与气候变量,在瑞士全国30米分辨率上制图,估计十种主要树种及Other类的地径断面积占比。

cs.CV

查看原文摘要

Tree-species composition shapes forest productivity and how forests respond to climate disturbances such as drought, windthrow and insect outbreaks. Yet most national forest maps assign each pixel a single dominant species and cannot show the share of accompanying species. We mapped the basal-area shares of ten main tree species and a residual Other class across Switzerland at 30 m resolution. A deep-learning model combining 0.1 m aerial RGB imagery, airborne laser scanning (ALS), annual AlphaEarth satellite embeddings, and climate variables was trained on basal-area observations from 3,992 Swiss National Forest Inventory (NFI) sites. In spatial cross-validation, the model reached a macro-$R^2$ of 0.485 across the 11 classes. On an independent forest-reserve dataset, the map reached a macro-$R^2$ of 0.552 for individual 30 m pixels and 0.733 for plots, and identified the dominant class in 73.2% of pixels and 81.1% of plots. The map shows maple and ash as widespread minor components that dominant-class maps omit. It also reproduces the elevational sequence from broadleaved lowland stands through spruce to larch and Arolla pine near the treeline. By resolving the species mixture within each 30 m pixel, the map complements field inventory statistics with spatially continuous information that can support forest monitoring, the management of mixed stands, and climate-adaptation planning across Switzerland.

新论文 · v1arXiv:2611.02909

Cloudra: Geometric Reasoning and Scientific Validation for Autonomous Reaction Mechanism Exploration

Chengyi Yang, Qianxin Zhou, Yang Li

原文摘要

Autonomous reaction-mechanism exploration requires proposing reaction steps, preparing three-dimensional structures, and determining which reactant and product a computed saddle point connects. Large language model (LLM) agents can misjudge spatial relationships and confuse a computed structure with the species or step they intended to study. We present Cloudra, a multi-agent framework that constrains mechanistic output through a Delivery DAG of chemical objects. Species nodes carry geometries and bonding topology; elementary-step edges carry transition states and reaction connections between species. Cheminformatics algorithms establish molecular identities and atom correspondences. Deterministic routines measure and transform structures to prepare candidate geometries. Frequency and IRC calculations determine the stationary points found and the species they connect. Agents use these objects to test proposed steps, compare pathways, and revise the mechanism. CloudraBench evaluates the framework's end-to-end mechanism-calculation capability across 50 tasks covering elementary reactions, multistep mechanisms, stereochemical competition, and computational method limitations. Across 200 runs under four workflow configurations, the primary Guided workflow achieves a mean composite score of 0.805, compared with 0.584 for the same-model Standard baseline. On Hard-tier tasks, the Guided mean increases from 0.689 under Standard to 0.958. Under Guided, the self-consistency component reaches its maximum score in 24 of the 40 non-Impossible tasks, compared with seven under Standard. Behavioral analyses examine how the agents use bond and dihedral measurements, optimized structures, and IRC endpoints to revise local mechanistic assignments.

cs.MA

新论文 · v1arXiv:2611.01943

Beyond Multimodal Emotion Conflict: Temporal Context-Aware Hidden Emotion Detection with Multimodal Large Language Models

Yonghao Wang, Jiaxin Zhou

原文摘要

Multimodal emotion recognition commonly combines textual, acoustic, and visual signals to infer affective states. Recent work has begun to study conflicts among modalities, but a conflict does not necessarily indicate that a person is concealing an emotion. It may also result from mixed emotions, individual expressive styles, or contextual factors. This proposal aims to distinguish ordinary emotional inconsistency from emotion concealment and to infer the underlying emotion when supported by evidence. We plan to construct a multimodal benchmark with explicit annotations of expressed emotion, internal emotion, and concealment conditions, and to develop an MLLM-based framework that integrates fine-grained facial Action Units (AUs), cross-modal features, and temporal context.

cs.AI

新论文 · v1arXiv:2611.01765

FinishStrong: Learning to End Well after Imperfect Start in Video Temporal Grounding

Yuda Zou, Boxiang Zhou, Xin Zhou, Yibo Chen, Dejia Song, Xu Tang, Yao Hu, Yongchao Xu

原文摘要

A poor start lowers the ceiling, but does not negate the value of finishing well. In autoregressive video temporal grounding, models systematically exhibit an endpoint performance asymmetry, predicting ends significantly worse than starts. A committed flawed start acts as an immutable physical constraint, irreversibly capping the attainable overlap as a sunk loss. While models should minimize the remaining conditional regret, standard post-training paradigms fail to teach this adaptation. Specifically, teacher-forced SFT suffers from strict prefix exposure bias, and holistic trajectory evaluation in standard GRPO inadvertently penalizes conditionally optimal ends if they follow a poor start. To address this, we introduce FinishStrong, a novel two-stage post-training framework explicitly designed to teach optimal continuations. First, Online-start SFT exposes the end prediction to the model's own generated contexts. Second, Conditional-tree GRPO restructures the sampling topology, centering end rewards exclusively within the same-start branch to mathematically isolate the conditional end quality from the inherited start penalty. FinishStrong-9B achieves a state-of-the-art 61.7\% overall IoU on TimeLens-Bench, remarkably outperforming flagship closed-source models like Gemini-3.8-Flash and Qwen3.8-Max. Crucially, when forced to continue from imperfect starts, it reduces the subsequent end prediction error by 36.5\%, proving its exceptional ability to end well after flawed starts. Code will be open.

cs.CV

新论文 · v1arXiv:2610.38999

A Spectral Boundary for Independence Learnability

Senhan Yao, Yuxin Zhou

原文摘要

Learning independence is fundamental to statistical inference and machine learning, yet learning independence between entire time series by a test remains challenging when only a single observation record is available. Existing guarantees often rely on structural or mixing assumptions, while stationarity and ergodicity alone do not permit consistent testing. In this work, we identify a class-level boundary governed by shared nontrivial Koopman eigenvalues, which represent common persistent oscillatory frequencies of the two processes. When no such eigenvalues are shared, we extend shift-based rank calibration with finite-window dependence witnesses and a data-adaptive threshold to construct a deterministic, weakly consistent test with finite-sample false-positive control, without quantitative mixing assumptions. Conversely, we show that no possibly randomized test can achieve vanishing false-positive probabilities under every independent jointly totally ergodic law while consistently detecting every dependent jointly totally ergodic law with a shared nontrivial eigenvalue. This impossibility already holds for binary observations and persists within any prescribed nonempty open eigenvalue window, identifying a spectral obstruction to universal learning of full-process independence.

math.ST · stat.ML

新论文 · v1arXiv:2610.37803

3Dtrees.earth: community research infrastructure for tree and forest analysis using close-range LiDAR data

Janusch Vajna-Jehle, Kilian Gerberding, Daniel Lusk, Teja Kattenborn, Julia Sophie Gäßler, Anna Göritz, Luis Kremer, Charlotte Lange 等 278 位作者

原文摘要

From individual trees to forest stands, three-dimensional structure shapes carbon, water, and energy flows, habitat conditions, and resource availability. Yet tree and forest structural attributes remain difficult to assess consistently across space and time. Close-range LiDAR (light detection and ranging) records detailed 3D structure from branches and trees to forest plots, including trees outside forests. However, broader reuse is constrained when data, acquisition context, processing, computation, and access conditions are maintained separately. We present 3Dtrees.earth, an operational community research infrastructure that brings close-range LiDAR datasets, analysis tools, and computing resources together while linking original observations to their metadata and processing outputs. As of 23 October 2026, the platform comprised 2,760 datasets, including 2,481 publicly visible datasets. These point cloud datasets span 46 countries on all six inhabited continents and include terrestrial, mobile, and uncrewed aerial laser scanning. Users can contribute and discover datasets, run standardized processing workflows on shared computing infrastructure, inspect point clouds and model predictions in the browser, and access data and processing outputs together with citation information. Workflows combine rule-based and machine-learning methods, with tools updated as methods advance. Outputs include raster products, individual-tree and semantic segmentation, and tree- and stand-level metrics. Original point clouds and processing records are retained, enabling reprocessing with improved tools while preserving provenance. With broader coverage, curation, and validation, this shared resource could extend individual surveys into a basis for model evaluation and benchmarking, cross-site synthesis, calibration and validation of larger-scale Earth observation products, and macroecological analysis.

cs.DL

新论文 · v1arXiv:2610.35311

Temporal-Difference Calibration of Black-Box Simulators

Min Zeng, Xin Wen, Xi Chen, Yichen Zhang, Wen-Xin Zhou

原文摘要

We develop a derivative-free temporal-difference (TD) framework for calibrating black-box simulators using one-step transitions from a target system and noisy simulator-generated continuation values. The calibration parameter is defined through Bellman orthogonality, recovering the physical parameter under correct simulator specification and yielding a near-optimal $L_2$ approximation of the policy value under misspecification. We propose three TD algorithms based on random-direction finite differences, distinguished by their query costs and reuse of noisy simulator evaluations. We establish almost-sure convergence, last-iterate mean-square error bounds, and central limit theorems for Polyak-Ruppert averages across four query-noise regimes. Our analysis reveals a specification-dependent bias phenomenon: for two algorithms, the finite-difference bias of the TD estimating equation vanishes at the calibration target under correct specification, even when the gradient surrogate remains biased. This permits a fixed perturbation radius and rate exponents approaching $1/2$ in the simulator rollout budget, whereas misspecification generally recovers the classical Kiefer-Wolfowitz rates. We also develop a few-replicate online bootstrap that yields Student-$t$ calibrated confidence intervals under negligible query noise, and identify a covariance mismatch that can invalidate conventional multiplier inference along Markov trajectories. Finally, a second-stage TD recursion corrects the remaining value discrepancy without additional simulator queries.

stat.ML · cs.LG

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1107ACL Anthology · ACL 2026

SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios

Junkai Chen, Huihui Huang Singapore Management University, Yunbo Lyu, Junwen An national university of singaore, National University of Singapore, Jieke Shi Singapore Management University, Chengran Yang, Ting Zhang Monash University, Haoye Tian 等 13 位作者

原文摘要

Large language model-powered code agents are rapidly transforming software engineering, yet the security risks of their generated code have become a critical concern. Existing benchmarks have provided valuable insights, but they fail to capture scenarios in which vulnerabilities are actually introduced by human developers, making fair comparisons between humans and agents infeasible. We therefore introduce SecureVibeBench, a benchmark of 105 C/C++ secure coding tasks sourced from 41 projects in OSS-Fuzz for code agents. SecureVibeBench has the following features: (i) realistic task settings that require multi-file edits in large repositories, (ii) aligned contexts based on real-world open-source vulnerabilities with precisely identified vulnerability introduction points, and (iii) comprehensive evaluation that combines functionality testing and security checking with both static and dynamic oracles. We evaluate 5 popular code agents like OpenHands, supported by 5 LLMs (e.g., Claude sonnet 4.5) on SecureVibeBench. Results show that current agents struggle to produce both correct and secure code, as even the best-performing one, produces merely 23.8% correct and secure solutions on SecureVibeBench.

cs.CL · cs.AI

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1481ACL Anthology · ACL 2026

SeCuRepair: Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework

Chengran Yang, Ting Zhang Monash University, Jinfeng Jiang Singapore Management University, Xin Zhou, Haoye Tian, Mingzhe Du Nanyang Technological University and National University of Singapore, Jieke Shi Singapore Management University, Junkai Chen 等 12 位作者

原文摘要

The rapid accumulation of software vulnerabilities has outpaced manual remediation, creating an urgent need for Automated Vulnerability Repair (AVR). However, existing methods suffer from syntactic overfitting, mimicking surface forms without understanding the underlying repair logic, and fail to generalize to complex fixes. To transcend these limitations, we propose SeCuRepair, a reliable, scalable, and efficient RL-based AVR framework. By introducing a semantic-aware reward, SeCuRepair optimizes for code semantic equivalence rather than lexical mimicry. Furthermore, SeCuRepair incorporates an expert-aligned reasoning mechanism that explicitly grounds patch generation in a structured diagnosis. Finally, SeCuRepair introduces a difficulty-based curriculum that progressively disentangles the optimization barriers of entangled multi-hunk repairs. Extensive evaluations on a rigorous repository-level split show that SeCuRepair substantially outperforms state-of-the-art baselines, as confirmed by both automatic evaluation and human study.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表