REVIEW 6 cited by
SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 6 Pith papers
-
From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair
Backward reasoning distilled from a repository's already-fixed issues, injected as prompts, lifts LLM repair success on SWE-Bench Lite by up to 10.4 Pass@1 points.
-
BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practice
A 32B LLM trained with progressive reinforcement learning on cold-start and user-feedback data fixes Go lint errors at 84.68% accuracy with 1.72% redundancy on a private ByteDance test set.
-
One Token to Fool LLM-as-a-Judge
LLM reward models falsely accept empty 'master key' responses such as ':' or 'Thought process:' across many models, and a fine-tuning defense reduces these false positives to near zero.
-
Agentic Software Engineering: Foundational Pillars and a Research Roadmap
SASE introduces a dual-modality framework (SE for Humans and SE for Agents) with workbenches and structured artifacts to turn agentic coding into a disciplined engineering practice.
-
MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution
MCTS-REFINE uses tree search plus strict ground-truth matching to build chain-of-thought training data that lifts open-source LLM issue-resolution scores on SWE-bench.
-
How Well Do Large Reasoning Models Translate? A Comprehensive Evaluation for Multi-Domain Machine Translation
Large reasoning models such as OpenAI-o1, DeepSeek-R1, and Gemini-2.0-Flash-Thinking score higher than traditional LLMs on semantic quality metrics in complex and document-level translation, but lag on BLEU and in ter...
Discussion (0). Sign in to comment.