English
Related papers

Related papers: AgentLens: Revealing The Lucky Pass Problem in SWE…

200 papers

The advancement of large language models (LLMs) and code agents has demonstrated significant potential to assist software engineering (SWE) tasks, such as autonomous issue resolution and feature addition. Existing AI for software…

Software Engineering · Computer Science 2025-09-22 Zhiyu Fan , Kirill Vasilevski , Dayi Lin , Boyuan Chen , Yihao Chen , Zhiqing Zhong , Jie M. Zhang , Pinjia He , Ahmed E. Hassan

AI-driven software development has rapidly advanced with the emergence of software development agents that leverage large language models (LLMs) to tackle complex, repository-level software engineering tasks. These agents go beyond just…

Software Engineering · Computer Science 2026-04-10 Zhi Chen , Wei Ma , Lingxiao Jiang

Graphical user interface (GUI) agents can substantially improve productivity by automating frequently executed long-latency tasks on mobile devices. However, existing evaluation benchmarks are still constrained to limited applications,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-25 Yue Cao , Yingyao Wang , Pi Bu , Jingxuan Xing , Wei Jiang , Zekun Zhu , Junpeng Ma , Sashuai Zhou , Tong Lu , Jun Song , Yu Cheng , Yuning Jiang , Bo Zheng

Software Engineering Agents (SWE agents) can autonomously perform development tasks on benchmarks like SWE Bench, but still face challenges when tackling complex and ambiguous real-world tasks. Consequently, SWE agents are often designed to…

Software Engineering · Computer Science 2025-10-13 Aayush Kumar , Yasharth Bajpai , Sumit Gulwani , Gustavo Soares , Emerson Murphy-Hill

The arrival of large language models (LLMs) capable of multi-step reasoning, tool use, and long-horizon planning has produced a qualitative shift in software engineering. Where earlier code-completion tools such as GitHub Copilot operated…

Software Engineering · Computer Science 2026-04-30 Happy Bhati

Existing benchmarks for AI coding agents focus on isolated, single-issue tasks such as fixing a bug or adding a small feature. However, real-world software engineering is a long-horizon endeavor: developers interpret high-level…

Software Engineering · Computer Science 2026-05-25 Tue Le , Minh V. T. Thai , Dung Nguyen Manh , Huy Phan Nhat , Nghi D. Q. Bui

The rapid progress in Automated Program Repair (APR) has been driven by advances in AI, particularly large language models (LLMs) and agent-based systems. SWE-Bench is a recent benchmark designed to evaluate LLM-based repair systems using…

Software Engineering · Computer Science 2026-02-06 Matias Martinez , Xavier Franch

Software engineering (SWE) agents are transitioning from code generation to full software development lifecycle automation. A critical phase in this lifecycle is specification design: transforming initial proposals into carefully considered…

Multiagent Systems · Computer Science 2026-05-29 Grant Hamblin , Kevin Song , Zhanda Zhu , Anand Jayarajan , Sihang Liu , Nandita Vijaykumar , Gennady Pekhimenko

Large language models are increasingly used as coding agents for software engineering tasks. Current benchmarks mainly evaluate whether the agent can correctly solve the request or fix the bugs. They largely treat tasks as independent and…

Software Engineering · Computer Science 2026-05-07 Jiayuan Zhu , Junde Wu , Minhao Hu , Shengda Zhu , Jiazhen Pan , Weixiang Shen , Yijun Yang , Fenglin Liu , Jianye Hao , Yueming Jin , Qirong Ho , Min Xu

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

Improving open-source models on real-world SWE tasks (solving GITHUB issues) faces two key challenges: 1) scalable curation of execution environments to train these models, and, 2) optimal scaling of test-time compute. We introduce…

Software Engineering · Computer Science 2025-04-11 Naman Jain , Jaskirat Singh , Manish Shetty , Liang Zheng , Koushik Sen , Ion Stoica

Research on applications of reinforcement learning (RL) to large language models has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code generation. While these problems can be viewed as…

Issue resolution, a complex Software Engineering (SWE) task integral to real-world development, has emerged as a compelling challenge for artificial intelligence. The establishment of benchmarks like SWE-bench revealed this task as…

Software Engineering · Computer Science 2026-01-21 Caihua Li , Lianghong Guo , Yanlin Wang , Daya Guo , Wei Tao , Zhenyu Shan , Mingwei Liu , Jiachi Chen , Haoyu Song , Duyu Tang , Hongyu Zhang , Zibin Zheng

We introduce SWE-Bench Pro, a substantially more challenging benchmark that builds upon the best practices of SWE-BENCH [25], but is explicitly designed to capture realistic, complex, enterprise-level problems beyond the scope of SWE-BENCH.…

Autonomous agents have rapidly matured as task executors and seen widespread deployment via harnesses such as OpenClaw. Safety concerns have rightly drawn growing research attention, and beneath them lie the values silently steering agent…

Artificial Intelligence · Computer Science 2026-05-12 Haonan Dong , Qiguan Feng , Kehan Jiang , Haoran Ye , Xin Zhang , Guojie Song

With the advancement of Agentic AI, researchers are increasingly leveraging autonomous agents to address challenges in software engineering (SE). However, the large language models (LLMs) that underpin these agents often function as black…

Software Engineering · Computer Science 2026-04-03 Jingyue Li , André Storhaug

Code Agent development is an extremely active research area, where a reliable performance metric is critical for tracking progress and guiding new developments. This demand is underscored by the meteoric rise in popularity of SWE-Bench.…

Software Engineering · Computer Science 2025-03-12 Konstantinos Vergopoulos , Mark Niklas Müller , Martin Vechev

As autonomous coding agents become capable of handling increasingly long-horizon tasks, they have gradually demonstrated the potential to complete end-to-end software development. Although existing benchmarks have recently evolved from…

Software Engineering · Computer Science 2026-05-19 Qingnan Ren , Shun Zou , Shiting Huang , Ziao Zhang , Kou Shi , Zhen Fang , Yiming Zhao , Yu Zeng , Qisheng Su , Lin Chen , Yong Wang , Zehui Chen , Xiangxiang Chu , Feng Zhao

As language agents increasingly automate critical tasks, their ability to follow domain-specific standard operating procedures (SOPs), policies, and constraints when taking actions and making tool calls becomes essential yet remains…

Computation and Language · Computer Science 2025-06-18 Zekun Li , Shinda Huang , Jiangtian Wang , Nathan Zhang , Antonis Antoniades , Wenyue Hua , Kaijie Zhu , Sirui Zeng , Chi Wang , William Yang Wang , Xifeng Yan

As LLM-based agents operate over sequential multi-step reasoning, hallucinations arising at intermediate steps risk propagating along the trajectory, thus degrading overall reliability. Unlike hallucination detection in single-turn…

Computation and Language · Computer Science 2026-01-13 Xuannan Liu , Xiao Yang , Zekun Li , Peipei Li , Ran He