SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wei, Yuxiang, Duchenne, Olivier, Copet, Jade, Carbonneaux, Quentin, Zhang, Lingming, Fried, Daniel, Synnaeve, Gabriel, Singh, Rishabh, Wang, Sida I.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909935582838784
author Wei, Yuxiang
Duchenne, Olivier
Copet, Jade
Carbonneaux, Quentin
Zhang, Lingming
Fried, Daniel
Synnaeve, Gabriel
Singh, Rishabh
Wang, Sida I.
author_facet Wei, Yuxiang
Duchenne, Olivier
Copet, Jade
Carbonneaux, Quentin
Zhang, Lingming
Fried, Daniel
Synnaeve, Gabriel
Singh, Rishabh
Wang, Sida I.
contents The recent DeepSeek-R1 release has demonstrated the immense potential of reinforcement learning (RL) in enhancing the general reasoning capabilities of large language models (LLMs). While DeepSeek-R1 and other follow-up work primarily focus on applying RL to competitive coding and math problems, this paper introduces SWE-RL, the first approach to scale RL-based LLM reasoning for real-world software engineering. Leveraging a lightweight rule-based reward (e.g., the similarity score between ground-truth and LLM-generated solutions), SWE-RL enables LLMs to autonomously recover a developer's reasoning processes and solutions by learning from extensive open-source software evolution data -- the record of a software's entire lifecycle, including its code snapshots, code changes, and events such as issues and pull requests. Trained on top of Llama 3, our resulting reasoning model, Llama3-SWE-RL-70B, achieves a 41.0% solve rate on SWE-bench Verified -- a human-verified collection of real-world GitHub issues. To our knowledge, this is the best performance reported for medium-sized (<100B) LLMs to date, even comparable to leading proprietary LLMs like GPT-4o. Surprisingly, despite performing RL solely on software evolution data, Llama3-SWE-RL has even emerged with generalized reasoning skills. For example, it shows improved results on five out-of-domain tasks, namely, function coding, library use, code reasoning, mathematics, and general language understanding, whereas a supervised-finetuning baseline even leads to performance degradation on average. Overall, SWE-RL opens up a new direction to improve the reasoning capabilities of LLMs through reinforcement learning on massive software engineering data.
format Preprint
id arxiv_https___arxiv_org_abs_2502_18449
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
Wei, Yuxiang
Duchenne, Olivier
Copet, Jade
Carbonneaux, Quentin
Zhang, Lingming
Fried, Daniel
Synnaeve, Gabriel
Singh, Rishabh
Wang, Sida I.
Software Engineering
Artificial Intelligence
Computation and Language
The recent DeepSeek-R1 release has demonstrated the immense potential of reinforcement learning (RL) in enhancing the general reasoning capabilities of large language models (LLMs). While DeepSeek-R1 and other follow-up work primarily focus on applying RL to competitive coding and math problems, this paper introduces SWE-RL, the first approach to scale RL-based LLM reasoning for real-world software engineering. Leveraging a lightweight rule-based reward (e.g., the similarity score between ground-truth and LLM-generated solutions), SWE-RL enables LLMs to autonomously recover a developer's reasoning processes and solutions by learning from extensive open-source software evolution data -- the record of a software's entire lifecycle, including its code snapshots, code changes, and events such as issues and pull requests. Trained on top of Llama 3, our resulting reasoning model, Llama3-SWE-RL-70B, achieves a 41.0% solve rate on SWE-bench Verified -- a human-verified collection of real-world GitHub issues. To our knowledge, this is the best performance reported for medium-sized (<100B) LLMs to date, even comparable to leading proprietary LLMs like GPT-4o. Surprisingly, despite performing RL solely on software evolution data, Llama3-SWE-RL has even emerged with generalized reasoning skills. For example, it shows improved results on five out-of-domain tasks, namely, function coding, library use, code reasoning, mathematics, and general language understanding, whereas a supervised-finetuning baseline even leads to performance degradation on average. Overall, SWE-RL opens up a new direction to improve the reasoning capabilities of LLMs through reinforcement learning on massive software engineering data.
title SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
topic Software Engineering
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2502.18449