SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning

TL;DR

SoRFT introduces a structured, two-stage training method for large language models that significantly improves issue resolution capabilities by decomposing tasks and leveraging reinforcement learning, outperforming existing open-source models.

Contribution

The paper presents a novel subtask-oriented reinforcement fine-tuning approach that enhances open-source LLMs for issue resolving, addressing generalization and cost issues of commercial models.

Findings

Achieves state-of-the-art performance on SWE-Bench datasets.

Significantly improves issue resolution accuracy.

Provides a cost-effective alternative to commercial models.

Abstract

Mainstream issue-resolving frameworks predominantly rely on commercial models, leading to high costs and privacy concerns. Existing training approaches for issue resolving struggle with poor generalization and fail to fully leverage open-source development resources. We propose Subtask-oriented Reinforced Fine-Tuning (SoRFT), a novel training approach to enhance the issue resolving capability of LLMs. We decomposes issue resolving into structured subtasks: file localization, function localization, line localization, and code edit generation. SoRFT consists of two training stages: (1) rejection-sampled supervised fine-tuning, Chain of Thought (CoT) data is filtered using ground-truth before fine-tuning the LLM, and (2) rule-based reinforcement learning, which leverages PPO with ground-truth based rewards. We evaluate the SoRFT-trained model on SWE-Bench Verified and SWE-Bench Lite, achieving state-of-the-art (SOTA) performance among open-source models (e.g., resolve 21.4% issues on SWE-Bench Verified with SoRFT-Qwen-7B). The experimental results demonstrate that SoRFT significantly enhances issue-resolving performance, improves model generalization, and provides a cost-efficient alternative to commercial models.