To this end, we develop a novel ASE method namedRepoUnderstander by guiding agents to comprehensively under-stand the whole repositories. Specifically, we first condense thecritical information of the whole repository into the repositoryknowledge graph in a top-to-down mode to decrease the complex-ity of repository. Subsequently, we empower the agents the abilityof understanding whole repository by proposing a Monte Carlotree search based repository exploration strategy. In addition, tobetter utilize the repository-level knowledge, we guide the agents tosummarize, analyze, and plan. Then, they can manipulate the toolsto dynamically acquire information and generate the patches tosolve the real-world GitHub issues.
论文提出了一种名为RepoUnderstander的新颖方法,该方法指导代理通过以下几个步骤来全面理解整个代码仓库:
- 构建代码仓库知识图谱:通过自上而下的方式将整个仓库的关键信息压缩成知识图谱,以降低仓库的复杂性。
- 基于蒙特卡洛树搜索的仓库探索策略:赋予代理理解整个仓库的能力,通过模拟多种路径并评估它们的奖励分数,逐步缩小搜索空间,引导代理关注最相关的区域。
- 信息利用与补丁生成:指导代理总结、分析和规划,然后操作工具动态获取信息并生成解决现实世界GitHub问题的补丁。