paper-with-me

홈 › Papers

Tool-integrated Reinforcement Learning for Repo Deep Search

2025-08-05 · Zexiong Ma, Chao Peng, Qunhong Zeng, Pengfei Gao, Yanzhen Zou, Bing Xie arxiv

Issue localization, the process of identifying code locations that need modification to resolve software issues, is a critical yet challenging task in software development. The semantic gap between natural language issue descriptions and faulty code requires complex multi-hop reasoning through code dependencies. Existing LLM-based agents attempt to address this by integrating repository retrieval tools. However, this transforms issue localization into a demanding task we call Repo Deep Search, which requires the LLM to effectively utilize various repository retrieval tools throughout a multi-step reasoning and navigation process. To tackle this challenge, we present ToolTrain, a two-stage tool-integrated training framework combining rejection-sampled supervised fine-tuning and tool-integrated reinforcement learning to enhance LLMs' ability to use retrieval tools for issue localization. Experimental results show that ToolTrain-trained models achieve state-of-the-art performance, with our 32B model even surpassing Claude-3.7 on function-level localization. The results also show that improved localization performance translates to better end-to-end issue resolution performance. This further demonstrates that training for issue localization is a viable and effective strategy for improving automated software development.

📄 PDF Abstract BibTeX arXiv:2508.03012

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Rollout Cards: A Reproducibility Standard for Agent Research

2026-05-12 · Charlie Masters, Ziyuan Liu, Stefano V. Albrecht arxiv

Reproducibility problems that have long affected machine learning and reinforcement learning are now surfacing in agent research: papers compare systems by reported scores while leaving the rollout records behind those s…

Reinforcement Learning

Technical Challenges of Deploying Reinforcement Learning Agents for Game Testing in AAA Games

2023-07-19 · Jonas Gillberg, Joakim Bergdahl, Alessandro Sestini, Andrew Eakins 외

Going from research to production, especially for large and complex software systems, is fundamentally a hard problem. In large-scale game production, one of the main reasons is that the development environment can be ve…

reinforcement-learningReinforcement Learning

ToRL: Scaling Tool-Integrated RL

2025-03-30 · Xuefeng Li, Haoyang Zou, PengFei Liu

We introduce ToRL (Tool-Integrated Reinforcement Learning), a framework for training large language models (LLMs) to autonomously use computational tools via reinforcement learning. Unlike supervised fine-tuning, ToRL al…

Mathreinforcement-learningReinforcement Learning

Q-Cogni: An Integrated Causal Reinforcement Learning Framework

2023-02-26 · Cris Cunha, Wei Liu, Tim French, Ajmal Mian

We present Q-Cogni, an algorithmically integrated causal reinforcement learning framework that redesigns Q-Learning with an autonomous causal structure discovery method to improve the learning process with causal inferen…

Causal InferenceDecision MakingQ-Learningreinforcement-learning+2

Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees

2026-01-13 · Kun Li, Zenan Xu, Junan Li, Zengrui Jin 외 arxiv

Tool-Integrated Reasoning has emerged as a key paradigm to augment Large Language Models (LLMs) with computational capabilities, yet integrating tool-use into long Chain-of-Thought (long CoT) remains underexplored, large…

Reinforcement Learning