让AI agent自动调试并优化环境配置，提升成功率与纠错能力。
EvoConfig: Self-Evolving Multi-Agent Systems for Efficient Autonomous Environment Configuration
- 多智能体协作+自我进化机制，动态调整修复优先级。
- 在Envbench上达78.1%成功率，比前人高7.1%。
- 擅长复杂错误诊断，推荐修复方案更准确有效。
可靠的可执行环境是大语言模型完成软件工程任务的基础。由于配置过程复杂繁琐，大规模配置效率较低。然而，现有方法通常忽略智能体行为的细粒度分析，难以应对复杂错误，导致配置失败。为解决这一瓶颈，我们提出EvoConfig，一个高效的环境配置框架，通过优化多智能体协作来构建正确的运行时环境。EvoConfig包含专家诊断模块，用于执行后细粒度分析，并具备自进化机制，使专家智能体能实时自我反馈并动态调整错误修复优先级。实验表明，EvoConfig在Repo2Run的420个仓库上达到与先前最先进方法Repo2Run相当的性能，同时在更困难的Envbench上取得78.1%的成功率，优于Repo2Run 7.1%。除了端到端成功率，EvoConfig还展现出更强的调试能力，在错误识别准确率和修复建议有效性方面均优于现有方法。
原文摘要 · Abstract (English)
A reliable executable environment is the foundation for ensuring that large language models solve software engineering tasks. Due to the complex and tedious construction process, large-scale configuration is relatively inefficient. However, most methods always overlook fine-grained analysis of the actions performed by the agent, making it difficult to handle complex errors and resulting in configuration failures. To address this bottleneck, we propose EvoConfig, an efficient environment configuration framework that optimizes multi-agent collaboration to build correct runtime environments. EvoConfig features an expert diagnosis module for fine-grained post-execution analysis, and a self-evolving mechanism that lets expert agents self-feedback and dynamically adjust error-fixing priorities in real time. Empirically, EvoConfig matches the previous state-of-the-art Repo2Run on Repo2Run's 420 repositories, while delivering clear gains on harder cases: on the more challenging Envbench, EvoConfig achieves a 78.1% success rate, outperforming Repo2Run by 7.1%. Beyond end-to-end success, EvoConfig also demonstrates stronger debugging competence, achieving higher accuracy in error identification and producing more effective repair recommendations than existing methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。