0

CodeR: Issue Resolving with Multi-Agent and Task Graphs

CodeR uses a multi-agent framework and predefined task graphs to resolve bugs and add features in code repositories, achieving 28.33% issue resolution on SWE-bench lite.

Year
2024
Venue
arXiv 2024
Authors
17
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2406.01304v3ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

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.

Authors

17