Related papers: CodeR: Issue Resolving with Multi-Agent and Task Graphs

CodeR: Issue Resolving with Multi-Agent and Task Graphs

URL: http://arxiv.org/abs/2406.01304v3
Date: Tue, 11 Jun 2024 03:52:03 GMT
Title: CodeR: Issue Resolving with Multi-Agent and Task Graphs
Authors: 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,
Abstract summary: GitHub issue resolving has attracted significant attention from academia and industry. We propose CodeR, which adopts a multi-agent framework and pre-defined task graphs to Repair & Resolve reported bugs. On SWE-bench lite, CodeR is able to solve 28.33% of issues, when submitting only once for each issue.
Score: 21.499576889342343
License: http://creativecommons.org/licenses/by/4.0/
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.

Related papers

Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios [13.949319911378826]
This study evaluated 4,892 patches from 10 top-ranked agents on 500 real-world GitHub issues. No single agent dominated, with 170 issues unresolved, indicating room for improvement. Most agents maintained code reliability and security, avoiding new bugs or vulnerabilities. Some agents increased code complexity, many reduced code duplication and minimized code smells.
arXiv Detail & Related papers (2024-10-16T11:33:57Z)
RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph [63.87660059104077]
We present RepoGraph, a plug-in module that manages a repository-level structure for modern AI software engineering solutions. RepoGraph substantially boosts the performance of all systems, leading to a new state-of-the-art among open-source frameworks.
arXiv Detail & Related papers (2024-10-03T05:45:26Z)
Enhancing Automated Program Repair with Solution Design [5.547148114448699]
We introduce DRCodePilot, an approach designed to augment GPT-4-Turbo's APR capabilities by incorporating DR into the prompt instruction. Our experimental results are impressive: DRCodePilot achieves a full-match ratio that is a remarkable 4.7x higher than when GPT-4 is utilized directly.
arXiv Detail & Related papers (2024-08-22T01:13:02Z)
MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains [54.117238759317004]
Massive Multitask Agent Understanding (MMAU) benchmark features comprehensive offline tasks that eliminate the need for complex environment setups. It evaluates models across five domains, including Tool-use, Directed Acyclic Graph (DAG) QA, Data Science and Machine Learning coding, Contest-level programming and Mathematics. With a total of 20 meticulously designed tasks encompassing over 3K distinct prompts, MMAU provides a comprehensive framework for evaluating the strengths and limitations of LLM agents.
arXiv Detail & Related papers (2024-07-18T00:58:41Z)
How to Understand Whole Software Repository? [64.19431011897515]
An excellent understanding of the whole repository will be the critical path to Automatic Software Engineering (ASE) We develop a novel method named RepoUnderstander by guiding agents to comprehensively understand the whole repositories. To better utilize the repository-level knowledge, we guide the agents to summarize, analyze, and plan.
arXiv Detail & Related papers (2024-06-03T15:20:06Z)
MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution [47.850418420195304]
Large Language Models (LLMs) have shown promise in code generation but face difficulties in resolving GitHub issues. We propose a novel Multi-Agent framework for GitHub Issue reSolution, MAGIS, consisting of four agents customized for software evolution.
arXiv Detail & Related papers (2024-03-26T17:57:57Z)
SCREWS: A Modular Framework for Reasoning with Revisions [58.698199183147935]
We present SCREWS, a modular framework for reasoning with revisions. We show that SCREWS unifies several previous approaches under a common framework. We evaluate our framework with state-of-the-art LLMs on a diverse set of reasoning tasks.
arXiv Detail & Related papers (2023-09-20T15:59:54Z)
RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation [96.75695811963242]
RepoCoder is a framework to streamline the repository-level code completion process. It incorporates a similarity-based retriever and a pre-trained code language model. It consistently outperforms the vanilla retrieval-augmented code completion approach.
arXiv Detail & Related papers (2023-03-22T13:54:46Z)
ADPTriage: Approximate Dynamic Programming for Bug Triage [0.0]
We develop a Markov decision process (MDP) model for an online bug triage task. We provide an ADP-based bug triage solution, called ADPTriage, which reflects downstream uncertainty in the bug arrivals and developers' timetables. Our result shows a significant improvement over the myopic approach in terms of assignment accuracy and fixing time.
arXiv Detail & Related papers (2022-11-02T04:42:21Z)
Predicting Issue Types on GitHub [8.791809365994682]
Ticket Tagger is a GitHub app analyzing the issue title and description through machine learning techniques. We empirically evaluated the tool's prediction performance on about 30,000 GitHub issues.
arXiv Detail & Related papers (2021-07-21T08:14:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.