--- title: SWE-RL by Meta — Reinforcement Learning for Software... description: Meta's SWE-RL paper proposes scaling reinforcement learning for real-world software engineering tasks, addressing limitations of models like DeepSeek R1 that... canonical: https://daily.dev/posts/swe-rl-by-meta-reinforcement-learning-for-software-engineering-llms-jcvhr8lmq twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: SWE-RL by Meta — Reinforcement Learning for Software Engineering LLMs | daily.dev og:description: Meta's SWE-RL paper proposes scaling reinforcement learning for real-world software engineering tasks, addressing limitations of models like DeepSeek R1 that... og:url: https://daily.dev/posts/swe-rl-by-meta-reinforcement-learning-for-software-engineering-llms-jcvhr8lmq og:image: https://api.daily.dev/og/posts/JCvhR8LMq.png og:image:alt: SWE-RL by Meta — Reinforcement Learning for Software Engineering LLMs og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # SWE-RL by Meta — Reinforcement Learning for Software Engineering LLMs **[AI Papers Academy](https://daily.dev/sources/aipapersacademy)** · 8 min read · 0 upvotes · 0 comments ## Summary Meta's SWE-RL paper proposes scaling reinforcement learning for real-world software engineering tasks, addressing limitations of models like DeepSeek R1 that focus on competitive programming. Researchers curated a dataset of ~11 million high-quality GitHub pull requests from 4.6 million repositories, using issue descriptions, comments, and code context as training inputs. The model (Llama 3 SWE-RL 70B) is trained using Group Relative Policy Optimization (GRPO) with a rule-based reward derived from similarity between predicted and actual merged patches. The resulting model achieves 41% pass@1 on SWE-bench Verified, setting a new state-of-the-art for open-source models under 100B parameters. Notably, RL training produces emergent general reasoning behaviors — including divide-and-conquer strategies and self-reflection — that transfer to out-of-domain tasks not seen during training, consistently outperforming supervised fine-tuning. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [13 Models and 4 Agents on SWE Tasks: Go, Java, Python, Rust, TS](https://daily.dev/posts/13-models-and-4-agents-on-swe-tasks-go-java-python-rust-ts-ithomlqxu) · Hacker News · 2 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#reinforcement-learning](https://daily.dev/tags/reinforcement-learning), [#llama](https://daily.dev/tags/llama) [View this post on daily.dev](https://daily.dev/posts/swe-rl-by-meta-reinforcement-learning-for-software-engineering-llms-jcvhr8lmq) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"SWE-RL by Meta — Reinforcement Learning for Software Engineering LLMs","url":"https://daily.dev/posts/swe-rl-by-meta-reinforcement-learning-for-software-engineering-llms-jcvhr8lmq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/swe-rl-by-meta-reinforcement-learning-for-software-engineering-llms-jcvhr8lmq"},"datePublished":"2026-04-19T08:04:43.449Z","dateModified":"2026-04-19T08:05:55.851Z","description":"Meta's SWE-RL paper proposes scaling reinforcement learning for real-world software engineering tasks, addressing limitations of models like DeepSeek R1 that...","image":"https://i.ytimg.com/vi/DimD-eX0DW8/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/DimD-eX0DW8/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AI Papers Academy","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AI Papers Academy","logo":"https://media.daily.dev/image/upload/s--O3RGOCh9--/f_auto,q_auto/v1776585874/logos/aipapersacademy","url":"https://daily.dev/sources/aipapersacademy"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/swe-rl-by-meta-reinforcement-learning-for-software-engineering-llms-jcvhr8lmq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,reinforcement-learning,llama","timeRequired":"PT8M","video":{"@type":"VideoObject","name":"SWE-RL by Meta — Reinforcement Learning for Software Engineering LLMs","description":"Meta's SWE-RL paper proposes scaling reinforcement learning for real-world software engineering tasks, addressing limitations of models like DeepSeek R1 that...","thumbnailUrl":"https://i.ytimg.com/vi/DimD-eX0DW8/sddefault.jpg","uploadDate":"2026-04-19T08:04:43.449Z","duration":"PT8M","url":"https://api.daily.dev/r/JCvhR8LMq","embedUrl":"https://www.youtube.com/embed/DimD-eX0DW8"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Papers Academy","item":"https://daily.dev/sources/aipapersacademy"},{"@type":"ListItem","position":3,"name":"SWE-RL by Meta — Reinforcement Learning for Software Engineering LLMs"}]} ```