Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.26287 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912678245564416 |
|---|---|
| author | Li, Guochang Liu, Yuchen Qin, Zhen Wang, Yunkun Zhong, Jianping Zhi, Chen Li, Binhua Huang, Fei Li, Yongbin Deng, Shuiguang |
| author_facet | Li, Guochang Liu, Yuchen Qin, Zhen Wang, Yunkun Zhong, Jianping Zhi, Chen Li, Binhua Huang, Fei Li, Yongbin Deng, Shuiguang |
| contents | Repository-level software engineering tasks require large language models (LLMs) to efficiently navigate and extract information from complex codebases through multi-turn tool interactions. Existing approaches face significant limitations: training-free, in-context learning methods struggle to guide agents effectively in tool utilization and decision-making based on environmental feedback, while training-based approaches typically rely on costly distillation from larger LLMs, introducing data compliance concerns in enterprise environments. To address these challenges, we introduce RepoSearch-R1, a novel agentic reinforcement learning framework driven by Monte-carlo Tree Search (MCTS). This approach allows agents to generate diverse, high-quality reasoning trajectories via self-training without requiring model distillation or external supervision. Based on RepoSearch-R1, we construct a RepoQA-Agent specifically designed for repository question-answering tasks. Comprehensive evaluation on repository question-answering tasks demonstrates that RepoSearch-R1 achieves substantial improvements of answer completeness: 16.0% enhancement over no-retrieval methods, 19.5% improvement over iterative retrieval methods, and 33% increase in training efficiency compared to general agentic reinforcement learning approaches. Our cold-start training methodology eliminates data compliance concerns while maintaining robust exploration diversity and answer completeness across repository-level reasoning tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_26287 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search Li, Guochang Liu, Yuchen Qin, Zhen Wang, Yunkun Zhong, Jianping Zhi, Chen Li, Binhua Huang, Fei Li, Yongbin Deng, Shuiguang Software Engineering Repository-level software engineering tasks require large language models (LLMs) to efficiently navigate and extract information from complex codebases through multi-turn tool interactions. Existing approaches face significant limitations: training-free, in-context learning methods struggle to guide agents effectively in tool utilization and decision-making based on environmental feedback, while training-based approaches typically rely on costly distillation from larger LLMs, introducing data compliance concerns in enterprise environments. To address these challenges, we introduce RepoSearch-R1, a novel agentic reinforcement learning framework driven by Monte-carlo Tree Search (MCTS). This approach allows agents to generate diverse, high-quality reasoning trajectories via self-training without requiring model distillation or external supervision. Based on RepoSearch-R1, we construct a RepoQA-Agent specifically designed for repository question-answering tasks. Comprehensive evaluation on repository question-answering tasks demonstrates that RepoSearch-R1 achieves substantial improvements of answer completeness: 16.0% enhancement over no-retrieval methods, 19.5% improvement over iterative retrieval methods, and 33% increase in training efficiency compared to general agentic reinforcement learning approaches. Our cold-start training methodology eliminates data compliance concerns while maintaining robust exploration diversity and answer completeness across repository-level reasoning tasks. |
| title | Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2510.26287 |