paper-with-me

홈 › Papers

CodeR: Issue Resolving with Multi-Agent and Task Graphs

2024-06-03 · Dong Chen, Shaoxin Lin, Muhan Zeng, Daoguang Zan, Jian-Gang Wang, Anton Cheshkov, Jun Sun, Hao Yu, Guoliang Dong, Artem Aliev, Jie Wang, Xiao Cheng, Guangtai Liang, Yuchi Ma, Pan Bian, Tao Xie, Qianxiang Wang

GitHub issue resolving recently has attracted significant attention from academia and industry. SWE-bench is proposed to measure the performance in resolving issues. In this paper, we propose CodeR, which adopts a multi-agent framework and pre-defined task graphs to Repair & Resolve reported bugs and add new features within code Repository. On SWE-bench lite, CodeR is able to solve 28.33% of issues, when submitting only once for each issue. We examine the performance impact of each design of CodeR and offer insights to advance this research direction.

📄 PDF Abstract BibTeX arXiv:2406.01304

Code (1)

nl2code/coder 공식 구현

Tasks

Bug fixing

Similar Papers 제목 키워드 기반

LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues

2024-11-21 · Yalan Lin, Yingwei Ma, Rongyu Cao, Binhua Li 외

Reproducing buggy code is the first and crucially important step in issue resolving, as it aids in identifying the underlying problems and validating that generated patches resolve the problem. While numerous approaches …

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

2025-04-03 · Daoguang Zan, Zhirong Huang, Wei Liu, Hanwu Chen 외

The task of issue resolving is to modify a codebase to generate a patch that addresses a given issue. However, existing benchmarks, such as SWE-bench, focus almost exclusively on Python, making them insufficient for eval…

Reinforcement Learning (RL)

Can Agents Fix Agent Issues?

2025-05-27 · Alfin Wijaya Rahardja, Junwei Liu, Weitong Chen, Zhenpeng Chen 외

LLM-based agent systems are emerging as a new software paradigm and have been widely adopted across diverse domains such as medicine, robotics, and programming. However, maintaining these systems requires substantial eff…

DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle

2026-01-27 · Yuheng Tang, Kaijie Zhu, Bonan Ruan, Chuqi Zhang 외 arxiv

Even though demonstrating extraordinary capabilities in code generation and software issue resolving, AI agents' capabilities in the full software DevOps cycle are still unknown. Different from pure code generation, hand…

Code Generation

Resolving Java Code Repository Issues with iSWE Agent

2026-03-11 · Jatin Ganhotra, Sami Serhan, Antonio Abu Nassar, Avraham Shinnar 외 arxiv

Resolving issues on code repositories is an important part of software engineering. Various recent systems automatically resolve issues using large language models and agents, often with impressive performance. Unfortuna…