English
Related papers

Related papers: CVE-Factory: Scaling Expert-Level Agentic Tasks fo…

200 papers

The rapid advancement of Large Language Models (LLMs) presents new opportunities for automated software vulnerability detection, a crucial task in securing modern codebases. This paper presents a comparative study on the effectiveness of…

Software Engineering · Computer Science 2026-01-05 Md Hasan Saju , Maher Muhtadi , Akramul Azim

The rapid deployment of AI agents in commercial settings has outpaced the development of evaluation methodologies that reflect production realities. Existing benchmarks measure agent capabilities through retrospectively curated tasks with…

Code generation has emerged as one of AI's highest-impact use cases, yet existing benchmarks measure isolated tasks rather than the complete "zero-to-one" process of building a working application from scratch. We introduce Vibe Code Bench,…

Software Engineering · Computer Science 2026-05-15 Hung Tran , Langston Nashold , Rayan Krishnan , Antoine Bigeard , Alex Gu

Interactive agent benchmarks face a tension between scalable construction and realistic workflow evaluation. Hand-authored tasks are expensive to extend and revise, while static prompt evaluation misses failures that only appear when agents…

Artificial Intelligence · Computer Science 2026-05-19 Yuxiang Lai , Peng Xia , Haonian Ji , Kaiwen Xiong , Kaide Zeng , Jiaqi Liu , Fang Wu , Jike Zhong , Zeyu Zheng , Cihang Xie , Huaxiu Yao

This paper introduces SecRepoBench, a benchmark to evaluate code agents on secure code completion in real-world repositories. SecRepoBench has 318 code completion tasks in 27 C/C++ repositories, covering 15 CWEs. We evaluate 29 standalone…

Cryptography and Security · Computer Science 2026-02-17 Chihao Shen , Connor Dilgren , Purva Chiniya , Luke Griffith , Yu Ding , Yizheng Chen

Large language models (LLMs) show remarkable potential to act as computer agents, enhancing human productivity and software accessibility in multi-modal tasks that require planning and reasoning. However, measuring agent performance in…

Existing Agent benchmarks suffer from two critical limitations: high environment interaction overhead (up to 41\% of total evaluation time) and imbalanced task horizon and difficulty distributions that make aggregate scores unreliable. To…

Artificial Intelligence · Computer Science 2026-04-13 Wang Yang , Chaoda Song , Xinpeng Li , Debargha Ganguly , Chuang Ma , Shouren Wang , Zhihao Dou , Yuli Zhou , Vipin Chaudhary , Xiaotian Han

IDE-Bench is a comprehensive framework for evaluating AI IDE agents on real-world software engineering tasks through an IDE-native tool interface. We present a Dockerized test harness that goes beyond raw terminal execution, granting models…

Software Engineering · Computer Science 2026-02-02 Spencer Mateega , Jeff Yang , Tiana Costello , Shaurya Jadhav , Nicole Tian , Agustin Garcinuño

Coding agents powered by large language models are increasingly expected to perform realistic software maintenance tasks beyond isolated issue resolution. Existing benchmarks have shifted toward realistic software evolution, but they rarely…

Software Engineering · Computer Science 2026-05-15 Man Ho Lam , Chaozheng Wang , Hange Liu , Jingyu Xiao , Haau-sing Li , Jen-tse Huang , Terry Yue Zhuo , Michael R. Lyu

LLM agents are expected to complete end-to-end units of work across software tools, business services, and local workspaces. Yet many agent benchmarks freeze a curated task set at release time and grade mainly the final response, making it…

Software Engineering · Computer Science 2026-05-04 Chenxin Li , Zhengyang Tang , Mingxin Huang , Yunlong Lin , Shijue Huang , Shengyuan Liu , Bowen Ye , Rang Li , Lei Li , Benyou Wang , Yixuan Yuan

AI agents are increasingly used to solve complex, multi-step tasks, but existing multi-agent frameworks remain brittle as workflows grow in scale and depth. Small errors at intermediate stages can propagate through agent interactions, while…

Artificial Intelligence · Computer Science 2026-05-26 Andy Xu , Yu-Wing Tai

Recent advances in code agents have enabled automated software development at the project level, supported by large language models (LLMs). However, existing benchmarks for code agent evaluation face two major limitations. First, creating…

Software Engineering · Computer Science 2026-03-24 Lingyue Fu , Bolun Zhang , Hao Guan , Yaoming Zhu , Lin Qiu , Weiwen Liu , Xuezhi Cao , Xunliang Cai , Weinan Zhang , Yong Yu

Evolving AI systems increasingly deploy multi-agent architectures where autonomous agents collaborate, share information, and delegate tasks through developing protocols. This connectivity, while powerful, introduces novel security risks.…

Cryptography and Security · Computer Science 2025-07-30 Gauri Sharma , Vidhi Kulkarni , Miles King , Ken Huang

Large Language Models (LLMs) have significantly aided developers by generating or assisting in code writing, enhancing productivity across various tasks. While identifying incorrect code is often straightforward, detecting vulnerabilities…

Software Engineering · Computer Science 2025-01-15 Jinjun Peng , Leyi Cui , Kele Huang , Junfeng Yang , Baishakhi Ray

Large language models are increasingly deployed as complex agentic systems that scale with task complexity. While prior work has extensively explored model- and system-level scaling, algorithm- and task-level scaling remain largely…

Artificial Intelligence · Computer Science 2026-04-21 Zizhang Luo , Yuhao Luo , Youwei Xiao , Yansong Xu , Runlin Guo , Yun Liang

Software vulnerability detection is critical in software en- gineering as security flaws arise from complex interactions across code structure, repository context, and runtime conditions. Existing meth- ods are limited by local code views,…

Software Engineering · Computer Science 2026-03-17 Renwei Meng , Haoyi Wu , Jingming Wang , Haoyan Bai

Large language models still struggle with contest-level programming, while many agentic remedies rely on massive inference-time sampling or expensive multi-stage post-training. We study when execution feedback reliably helps an LLM CP…

Computation and Language · Computer Science 2026-05-26 Peisong Wang , Bowen Liu , Zehua Li , Yuyao Wang , Zhiwei Ma , Yuhan Li , Jia Li

Automated code vulnerability detection is critical for software security, yet existing approaches face a fundamental trade-off between detection accuracy and computational cost. We propose a heterogeneous multi-agent architecture inspired…

Cryptography and Security · Computer Science 2026-04-24 Zhaohui Geoffrey Wang

Large language model (LLM) agents are increasingly deployed to automate productivity tasks (e.g., email, scheduling, document management), but evaluating them on live services is risky due to potentially irreversible changes. Existing…

AI agents have the potential to significantly alter the cybersecurity landscape. Here, we introduce the first framework to capture offensive and defensive cyber-capabilities in evolving real-world systems. Instantiating this framework with…