DeepRepoQA: Code Repository Question Answering with Deep Agent Exploration

2026-08-25

AI Summary

为解决软件仓库中深层次代码理解和复杂架构查询问题，提出DeepRepoQA框架，采用蒙特卡洛树搜索机制引导的代理进行系统探索。

Abstract

Answering developer questions about a software repository is a critical yet under-explored problem in software engineering. While existing repository understanding methods have advanced the field, they predominantly rely on surface-level code retrieval and lack the ability for deep reasoning over multiple files, complex software architectures, and grounding answers in long-range code dependencies. To address these limitations, we propose DeepRepoQA, a novel question answering (QA) framework for repository-level code understanding. DeepRepoQA builds on an agentic framework where LLM agents find answers through a systematic tree search over the repository structure. A Monte-Carlo Tree Search (MCTS) mechanism is employed to empower agents to dynamically search, navigate, and inspect code, enabling effective multi-hop reasoning over long-range code dependencies. Comprehensive experiments on the SWE-QA benchmark demonstrate substantial performance gains over strong baselines, validating the effectiveness of systematic MCTS-guided exploration for multi-hop repository reasoning.

Problem

• software repository
• question answering
• deep reasoning
• code dependencies
• repository understanding

Innovation

• DeepRepoQA
• Monte-Carlo Tree Search (MCTS)
• multi-hop reasoning