研究称自动化代码评审中单智能体(SA)足以媲美甚至超越多智能体(MA)系统
When Single Agent Is Enough: Rethinking Multi-Agent Systems for Automated Code Review
AI 导读
arXiv 论文系统比较了代码评审意见生成(RCG)与代码精炼(CR)两类任务中的多智能体(MA)与单智能体(SA)设计。结果显示,设计更简单的 SA 方案表现与 MA 系统相当,某些任务上甚至更优。这一发现挑战了 MA 架构是复杂软件工程任务默认选择的主流假设。
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