EvoConfig: Self-Evolving Multi-Agent Systems for Efficient Autonomous Environment Configuration
This addresses the bottleneck of complex environment configuration for software engineering with AI, offering incremental improvements in efficiency and debugging competence.
The paper tackles the problem of inefficient and failure-prone environment configuration for large language models in software engineering tasks by proposing EvoConfig, a multi-agent framework with fine-grained analysis and self-evolving mechanisms, achieving a 78.1% success rate on a challenging benchmark, outperforming the previous state-of-the-art by 7.1%.
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.