English
Related papers

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

200 papers

Recent advances in large language models (LLMs) have enabled software engineering agents to tackle complex code modification tasks. Most existing approaches rely on execution feedback from containerized environments, which require…

Large language models and agents have achieved remarkable progress in code generation. However, existing benchmarks focus on isolated function/class-level generation (e.g., ClassEval) or modifications to existing codebases (e.g.,…

Software Engineering · Computer Science 2026-04-16 Zhiyuan Peng , Xin Yin , Pu Zhao , Fangkai Yang , Lu Wang , Ran Jia , Xu Chen , Qingwei Lin , Saravan Rajmohan , Dongmei Zhang

Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated files, wipes a stale credentials backup, or rewrites…

Software Engineering · Computer Science 2026-05-19 Yubin Qu , Ying Zhang , Yanjun Zhang , Gelei Deng , Yuekang Li , Leo Yu Zhang , Yi Liu

Software issue localization, the task of identifying the precise code locations (files, classes, or functions) relevant to a natural language issue description (e.g., bug report, feature request), is a critical yet time-consuming aspect of…

Software Engineering · Computer Science 2026-04-23 Revanth Gangi Reddy , Tarun Suresh , JaeHyeok Doo , Ye Liu , Xuan Phi Nguyen , Yingbo Zhou , Semih Yavuz , Caiming Xiong , Heng Ji , Shafiq Joty

The SWE-Bench Verified leaderboard is approaching saturation, with the top system achieving 78.80%. However, we show that this performance is inflated. Our re-evaluation reveals that one in five "solved" patches from the top-30 agents are…

Static benchmarks measure what AI agents can do at a fixed point in time but not how they are adopted, maintained, or experienced in deployment. We introduce AgentPulse, a continuous evaluation framework scoring 50 agents across 10 workload…

Artificial Intelligence · Computer Science 2026-04-28 Yuxuan Gao , Megan Wang , Yi Ling Yu

The Rust programming language presents a steep learning curve and significant coding challenges, making the automation of issue resolution essential for its broader adoption. Recently, LLM-powered code agents have shown remarkable success…

Software Engineering · Computer Science 2026-02-27 Jiahong Xiang , Wenxiao He , Xihua Wang , Hongliang Tian , Yuqun Zhang

Semantic code search, retrieving code that matches a given natural language query, is an important task to improve productivity in software engineering. Existing code search datasets face limitations: they rely on human annotators who…

Software Engineering · Computer Science 2026-02-05 Jing Gong , Yanghui Wu , Linxi Liang , Yanlin Wang , Jiachi Chen , Mingwei Liu , Zibin Zheng

Rigorous software testing is crucial for developing and maintaining high-quality code, making automated test generation a promising avenue for both improving software quality and boosting the effectiveness of code generation methods.…

Software Engineering · Computer Science 2025-02-10 Niels Mündler , Mark Niklas Müller , Jingxuan He , Martin Vechev

As Large Language Model (LLM) agents are increasingly deployed in open-ended domains like software engineering, they frequently encounter underspecified instructions that lack crucial context. While human developers naturally resolve…

Computation and Language · Computer Science 2026-03-30 Nicholas Edwards , Sebastian Schuster

Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, but their proficiency in producing secure code remains a critical, under-explored area. Existing benchmarks often fall short by relying on synthetic…

Cryptography and Security · Computer Science 2026-02-02 Yanlin Wang , Ziyao Zhang , Chong Wang , Xinyi Xu , Mingwei Liu , Yong Wang , Jiachi Chen , Zibin Zheng

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

Modern web applications are increasingly produced through AI-assisted development and rapid no-code deployment pipelines, widening the gap between accelerating software velocity and the limited adaptability of existing security tooling.…

Cryptography and Security · Computer Science 2026-03-03 Akshat Singh Jaswal , Ashish Baghel

The increasing adoption of AI coding agents has increased the number of agent-generated pull requests (PRs) merged with little or no human intervention. Although such PRs promise productivity gains, their post-merge code quality remains…

Software Engineering · Computer Science 2026-01-29 Shamse Tasnim Cynthia , Al Muttakin , Banani Roy

We introduce ISO-Bench, a benchmark for coding agents to test their capabilities on real-world inference optimization tasks. These tasks were taken from vLLM and SGLang, two of the most popular LLM serving frameworks. Each task provides an…

Machine Learning · Computer Science 2026-02-24 Ayush Nangia , Shikhar Mishra , Aman Gokrani , Paras Chopra

Automated issue solving seeks to autonomously identify and repair defective code snippets across an entire codebase. SWE-Bench has emerged as the most widely adopted benchmark for evaluating progress in this area. While LLM-based agentic…

Software Engineering · Computer Science 2025-09-18 Simiao Liu , Fang Liu , Liehao Li , Xin Tan , Yinghao Zhu , Xiaoli Lian , Li Zhang

Current search techniques are limited to standard RAG query-document applications. In this paper, we propose a novel technique to expand the code and index for predicting the required APIs, directly enabling high-quality, end-to-end code…

Software Engineering · Computer Science 2025-10-01 Esakkivel Esakkiraja , Denis Akhiyarov , Aditya Shanmugham , Chitra Ganapathy

LLM-based coding agents have shown strong performance on automated issue resolution benchmarks, yet existing evaluations largely focus on final task success, providing limited insight into how agents retrieve and use code context during…

Machine Learning · Computer Science 2026-02-12 Han Li , Letian Zhu , Bohan Zhang , Rili Feng , Jiaming Wang , Yue Pan , Earl T. Barr , Federica Sarro , Zhaoyang Chu , He Ye

Large language models that enhance software development tasks, such as code generation, code completion, and code question answering (QA), have been extensively studied in both academia and the industry. The models are integrated into…

Software Engineering · Computer Science 2025-01-08 Jialiang Chen , Kaifa Zhao , Jie Liu , Chao Peng , Jierui Liu , Hang Zhu , Pengfei Gao , Ping Yang , Shuiguang Deng

Understanding and reasoning about code semantics is essential for enhancing code LLMs' abilities to solve real-world software engineering (SE) tasks. Although several code reasoning benchmarks exist, most rely on synthetic datasets or…

Software Engineering · Computer Science 2026-02-05 Monoshi Kumar Roy , Simin Chen , Benjamin Steenhoek , Jinjun Peng , Gail Kaiser , Baishakhi Ray , Wei Le