English
Related papers

Related papers: BeyondSWE: Can Current Code Agent Survive Beyond S…

200 papers

Modern human labor is characterized by specialization; we train for years and develop particular tools that allow us to perform well across a variety of tasks. In addition, AI agents have been specialized for domains such as software…

Computation and Language · Computer Science 2025-06-04 Aditya Bharat Soni , Boxuan Li , Xingyao Wang , Valerie Chen , Graham Neubig

Prior representative ReAct-style approaches in autonomous Software Engineering (SWE) typically lack the explicit System-2 reasoning required for deep analysis and handling complex edge cases. While recent reasoning models demonstrate the…

Artificial Intelligence · Computer Science 2026-04-14 Shuquan Lian , Juncheng Liu , Yazhe Chen , Yuhong Chen , Hui Li

Large Language Models (LLMs) have demonstrated remarkable proficiency across a variety of complex tasks. One significant application of LLMs is in tackling software engineering challenges, particularly in resolving real-world tasks on…

Computation and Language · Computer Science 2025-05-08 Chengxing Xie , Bowen Li , Chang Gao , He Du , Wai Lam , Difan Zou , Kai Chen

Automatically resolving software issues is crucial for software development in practice, impacting the software quality and user experience. The process of resolving real-world issues encompasses tasks such as question-answering (QA), fault…

Software Engineering · Computer Science 2024-11-28 Ruida Hu , Chao Peng , Jingyi Ren , Bo Jiang , Xiangxin Meng , Qinyun Wu , Pengfei Gao , Xinchen Wang , Cuiyun Gao

Automated issue solving aims to resolve real-world issues in software repositories. The most popular benchmarks for automated issue solving are SWE-bench and its human-filtered subset SWE-bench Verified. These benchmarks leverage testing to…

Software Engineering · Computer Science 2025-09-10 You Wang , Michael Pradel , Zhongxin Liu

Autonomous agents are increasingly expected to support scientific research, and recent benchmarks report progress in code repair and autonomous experimentation. However, these evaluations typically assume a pre-configured execution…

Software Engineering · Computer Science 2026-03-12 Yubang Wang , Chenxi Zhang , Bowen Chen , Zezheng Huai , Zihao Dai , Xinchi Chen , Yuxin Wang , Yining Zheng , Jingjing Gong , Xipeng Qiu

As large language models (LLMs) become increasingly capable and widely adopted, benchmarks play a central role in assessing their practical utility. For example, SWE-Bench Verified has emerged as a critical benchmark for evaluating LLMs'…

Artificial Intelligence · Computer Science 2025-12-02 Shanchao Liang , Spandan Garg , Roshanak Zilouchian Moghaddam

Deep research agents have emerged as powerful systems for addressing complex queries. Meanwhile, LLM-based retrievers have demonstrated strong capability in following instructions or reasoning. This raises a critical question: can LLM-based…

Information Retrieval · Computer Science 2026-02-09 Tiansheng Hu , Yilun Zhao , Canyu Zhang , Arman Cohan , Chen Zhao

Software security vulnerabilities can lead to severe consequences, making early detection essential. Although code review serves as a critical defense mechanism against security flaws, relevant feedback remains scarce due to limited…

Software Engineering · Computer Science 2026-01-06 Zixiao Zhao , Yanjie Jiang , Hui Liu , Kui Liu , Lu Zhang

Verification is critical for improving agents: it provides the reward signal for Reinforcement Learning and enables inference-time gains through Test-Time Scaling (TTS). Despite its importance, verification in software engineering (SWE)…

Machine Learning · Computer Science 2026-01-08 Mohit Raghavendra , Anisha Gunjal , Bing Liu , Yunzhong He

Large language model (LLM) agents have recently shown strong performance on repository-level issue resolution, but existing systems are almost exclusively designed for Python and rely heavily on lexical retrieval and shallow code…

Software Engineering · Computer Science 2025-11-21 Qingao Dong , Mengfei Wang , Hengzhi Zhang , Zhichao Li , Yuan Yuan , Mu Li , Xiang Gao , Hailong Sun , Chunming Hu , Weifeng Lv

Recent advancements in Large Language Models (LLMs) have spurred interest in deploying LLM agents to undertake tasks in the world. LLMs are often deployed in agent systems: code that orchestrates LLM calls and provides them with tools. We…

Artificial Intelligence · Computer Science 2025-05-20 Maxime Robeyns , Martin Szummer , Laurence Aitchison

OpenClaw's ClawHub marketplace hosts tens of thousands of community-contributed agent skills (49,592 in our 2026-04-04 snapshot), and recent audits report that 13-26% contain security vulnerabilities. Regex scanners miss obfuscated…

Cryptography and Security · Computer Science 2026-05-27 Yinghan Hou , Zongyou Yang , Zaihu Pang , Xiujun Ma

As large language models (LLMs) evolve into autonomous agents, evaluating repository-level reasoning, the ability to maintain logical consistency across massive, real-world, interdependent file systems, has become critical. Current…

Software Engineering · Computer Science 2026-05-05 Jia Li , Yuxin Su , Michael R. Lyu

Issue localization, which identifies faulty code elements such as files or functions, is critical for effective bug fixing. While recent LLM-based and LLM-agent-based approaches improve accuracy, they struggle in large-scale repositories…

Software Engineering · Computer Science 2025-10-07 Ying Wang , Wenjun Mao , Chong Wang , Zhenhao Zhou , Yicheng Zhou , Wenyun Zhao , Yiling Lou , Xin Peng

Code repair is a fundamental task in software development, facilitating efficient bug resolution and software maintenance. Although large language models (LLMs) have demonstrated considerable potential in automated code repair, their…

Software Engineering · Computer Science 2026-02-27 Dekun Dai , MingWei Liu , Anji Li , Jialun Cao , Yanlin Wang , Chong Wang , Xin Peng , Zibin Zheng

AI coding agents increasingly modify real software repositories and make dependency decisions, including adding, removing, or updating third-party packages. These choices can materially affect security posture and maintenance burden, yet…

Software Engineering · Computer Science 2026-02-02 Tanmay Singla , Berk Çakar , Paschal C. Amusuo , James C. Davis

Code completion, a key downstream task in code generation, is one of the most frequent and impactful methods for enhancing developer productivity in software development. As intelligent completion tools evolve, we need a robust evaluation…

Software Engineering · Computer Science 2024-10-25 Zhenyu Pan , Rongyu Cao , Yongchang Cao , Yingwei Ma , Binhua Li , Fei Huang , Han Liu , Yongbin Li

LLM-based agents score well on search benchmarks, yet real users consistently find results unsatisfying, revealing a persistent evaluation-experience gap. We attribute this gap to existing benchmarks' reliance on over-specified queries,…

Computation and Language · Computer Science 2026-05-28 Xiaohongshu Inc

Repository-level fault localization (FL) and automated program repair (APR) require an agent to identify the relevant code units across files, follow call and data dependencies, and generate a valid patch. Existing graph-based systems…

Software Engineering · Computer Science 2026-05-06 Shahd Seddik , Fatemeh Fard