One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents

• URL: http://arxiv.org/abs/2512.20957v2
• Date: Thu, 25 Dec 2025 05:33:05 GMT
• Title: One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents
• Authors: Zhaoxi Zhang, Yitong Duan, Yanzhi Zhang, Yiming Xu, Jiyan He, Yunfang Wu,
• Abstract summary: RepoNavigator is an agent equipped with a single execution-aware tool-jumping to the definition of an invoked symbol.<n>RepoNavigator is trained end-to-end via Reinforcement Learning directly from a pretrained model, without any closed-source distillation.
• Score: 16.281864564259827
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Locating the files and functions requiring modification in large open-source software (OSS) repositories is challenging due to their scale and structural complexity. Existing large language model (LLM)-based methods typically treat this as a repository-level retrieval task and rely on multiple auxiliary tools, which 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 pretrained model, without any 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 even the 32B model exceeding closed-source models such as Claude-3.7. These results confirm that integrating a single, structurally grounded tool with RL training provides an efficient and scalable solution for repository-level issue localization.

Related papers

• Pull Requests as a Training Signal for Repo-Level Code Editing [49.82435173554125]
  Clean Pull Request (Clean-PR) is a mid-training paradigm that leverages real-world GitHub pull requests as a training signal for repository-level editing.<n>We introduce a scalable pipeline that converts noisy pull request diffs into Search/Replace edit blocks through reconstruction and validation.<n>On SWE-bench, our model significantly outperforms the instruction-tuned baseline, achieving absolute improvements of 13.6% on SWE-bench Lite and 12.3% on SWE-bench Verified.
  arXiv  Detail & Related papers  (2026-02-07T09:22:25Z)
• D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use [17.99381644283042]
  Large reasoning models (LRMs) lack the capability of sub-task decomposition in complex tool use scenarios, leading to Lazy Reasoning.<n>We propose a two-stage training framework that incentivizes LRMs' task decomposition reasoning capability via self-distillation and diversity-aware reinforcement learning.<n>D-CORE achieves robust tool-use improvements across diverse benchmarks and model scales.
  arXiv  Detail & Related papers  (2026-02-02T14:36:15Z)
• LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls [46.34510189812439]
  LoopTool is a fully automated, model-aware data evolution framework.<n>It iteratively refines both the data and the model through three synergistic modules.<n> Experiments show that our 8B model trained with LoopTool significantly surpasses its 32B data generator.
  arXiv  Detail & Related papers  (2025-11-12T09:34:39Z)
• Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch [63.40752011615843]
  Training tool-augmented language models has emerged as a promising approach to enhancing their capabilities for complex tasks.<n>We propose a dynamic generalization-guided reward design for rule-based reinforcement learning.<n>We show that our models achieve over 7% performance improvement compared to both SFT and RL-with-SFT models.
  arXiv  Detail & Related papers  (2025-11-02T16:33:45Z)
• Reinforcement Learning for Machine Learning Engineering Agents [52.03168614623642]
  We show that agents backed by weaker models that improve via reinforcement learning can outperform agents backed by much larger, but static models.<n>We propose duration- aware gradient updates in a distributed asynchronous RL framework to amplify high-cost but high-reward actions.<n>We also propose environment instrumentation to offer partial credit, distinguishing almost-correct programs from those that fail early.
  arXiv  Detail & Related papers  (2025-09-01T18:04:10Z)
• VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use [78.29315418819074]
  We introduce VerlTool, a unified and modular framework that addresses limitations through systematic design principles.<n>Our framework formalizes ARLT as multi-turn trajectories with multi-modal observation tokens (text/image/video), extending beyond single-turn RLVR paradigms.<n>The modular plugin architecture enables rapid tool integration requiring only lightweight Python definitions.
  arXiv  Detail & Related papers  (2025-09-01T01:45:18Z)
• RLFactory: A Plug-and-Play Reinforcement Learning Post-Training Framework for LLM Multi-Turn Tool-Use [50.52940111891476]
  Large language models excel at basic reasoning but struggle with tasks that require interaction with external tools.<n>We present RLFactory, a plug-and-play reinforcement learning framework for multi-round tool use.
  arXiv  Detail & Related papers  (2025-08-31T16:47:31Z)
• On the Impacts of Contexts on Repository-Level Code Generation [5.641402231731082]
  We present RepoExec, a novel benchmark designed to evaluate repository-level code generation.<n>We focus on three key aspects: executability, functional correctness through comprehensive test case generation, and accurate utilization of cross-file contexts.
  arXiv  Detail & Related papers  (2024-06-17T10:45:22Z)
• CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets [75.64181719386497]
  We present CRAFT, a tool creation and retrieval framework for large language models (LLMs) It creates toolsets specifically curated for the tasks and equips LLMs with a component that retrieves tools from these sets to enhance their capability to solve complex tasks. Our method is designed to be flexible and offers a plug-and-play approach to adapt off-the-shelf LLMs to unseen domains and modalities, without any finetuning.
  arXiv  Detail & Related papers  (2023-09-29T17:40:26Z)
• Integrating Distributed Architectures in Highly Modular RL Libraries [4.297070083645049]
  Most popular reinforcement learning libraries advocate for highly modular agent composability. We propose a versatile approach that allows the definition of RL agents at different scales through independent reusable components.
  arXiv  Detail & Related papers  (2020-07-06T10:22:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.