{"ID":2825380,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.20957","arxiv_id":"2512.20957","title":"One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents","abstract":"Locating files and functions requiring modification in large software repositories is challenging due to their scale and structural complexity. Existing LLM-based methods typically treat this as a repository-level retrieval task and rely on multiple auxiliary tools, which often overlook code execution logic and complicate model control. We propose RepoNavigator, an LLM agent equipped with a single execution-aware tool: jumping to the definition of an invoked symbol. This unified design reflects the actual flow of code execution while simplifying tool manipulation. RepoNavigator is trained end-to-end via Reinforcement Learning (RL) directly from a base pretrained model, without relying on closed-source distillation. Experiments demonstrate that RL-trained RepoNavigator achieves state-of-the-art performance, with the 7B model outperforming 14B baselines, the 14B model surpassing 32B competitors, and the 32B model exceeding closed-source models such as GPT-5 on most metrics. These results confirm that integrating a single, structurally grounded tool with RL training provides an efficient and scalable solution for repository-level issue localization.","short_abstract":"Locating files and functions requiring modification in large software repositories is challenging due to their scale and structural complexity. Existing LLM-based methods typically treat this as a repository-level retrieval task and rely on multiple auxiliary tools, which often overlook code execution logic and complic...","url_abs":"https://arxiv.org/abs/2512.20957","url_pdf":"https://arxiv.org/pdf/2512.20957v6","authors":"[\"Zhaoxi Zhang\",\"Yitong Duan\",\"Yanzhi Zhang\",\"Yiming Xu\",\"Zhixiang Wang\",\"Kun Liang\",\"Weikang Li\",\"Jiahui Liang\",\"Deguo Xia\",\"Jizhou Huang\",\"Jiyan He\",\"Yunfang Wu\"]","published":"2025-12-24T05:27:53Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\"]","has_code":false}