arXiv cs.AI· Jiawei Li, Hoa Khanh Dam, Iftekhar Ahmed·· 10 小时前AI 评分34
单智能体就够了:重新审视用于自动化代码审查的多智能体系统
When Single Agent Is Enough: Rethinking Multi-Agent Systems for Automated Code Review
AI 导读
一项系统对比发现,在代码审查评论生成(RCG)和代码改进(CR)任务上,单智能体(SA)方案表现与多智能体(MA)系统相当,有时甚至更优,尽管设计更简单。MA 系统虽通过协调专注不同质量维度的智能体取得过 SOTA 结果,却带来显著的架构复杂度和运行时开销。该结果挑战了 MA 架构是复杂软件工程任务默认选择的普遍假设。
正文 · 原文
Abstract:Code review plays a critical role in identifying software quality issues and ensuring system robustness. Prior work has proposed techniques for Review Comment Generation (RCG) and Code Refinement (CR), with recent Multi-Agent (MA) approaches achieving state-of-the-art results by coordinating agents specialized in different quality dimensions. However, MA systems introduce substantial architectural complexity and runtime overhead, and recent evidence suggests they may underperform Single-Agent (SA) approaches in certain tasks. In this work, we systematically compare MA and SA designs for RCG and CR. Surprisingly, our results show that SA approaches perform comparably to- and sometimes outperform-MA systems, despite their simpler design. These findings challenge the prevailing assumption that MA architectures are the default choice for complex software engineering tasks.
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.23283 [cs.SE] |
| (or arXiv:2611.23283v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23283 arXiv-issued DOI via DataCite |
Submission history
From: Jiawei Li [view email]
[v1]
Sat, 24 Oct 2026 00:15:37 UTC (6,796 KB)
来源:arXiv cs.AI · arxiv.org