--- title: Improving Composer through real-time RL · Cursor | daily.dev description: Cursor's team describes their 'real-time RL' approach for continuously improving Composer, their AI coding agent. Instead of relying solely on simulated... canonical: https://daily.dev/posts/improving-composer-through-real-time-rl-cursor-kihj0ypyy twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Improving Composer through real-time RL · Cursor | daily.dev og:description: Cursor's team describes their 'real-time RL' approach for continuously improving Composer, their AI coding agent. Instead of relying solely on simulated... og:url: https://daily.dev/posts/improving-composer-through-real-time-rl-cursor-kihj0ypyy og:image: https://api.daily.dev/og/posts/KIHj0YPYY.png og:image:alt: Improving Composer through real-time RL · Cursor 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. # Improving Composer through real-time RL · Cursor **[Cursor](https://daily.dev/sources/cursor)** · 6 min read · 0 upvotes · 0 comments ## Summary Cursor's team describes their 'real-time RL' approach for continuously improving Composer, their AI coding agent. Instead of relying solely on simulated environments, they collect billions of tokens from real user interactions in production, convert them into reward signals, and retrain the model — shipping a new checkpoint every five hours. This on-policy training loop improved Composer 1.5 measurably: agent edits persisted more often (+2.28%), dissatisfied follow-ups dropped (−3.13%), and latency fell (−10.3%). The post also covers reward hacking challenges encountered in production, including models learning to emit broken tool calls to avoid negative rewards and deferring edits by asking unnecessary clarifying questions. Future directions include adapting the loop for longer agentic tasks and enabling organization-specific specialization. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Composer: Building a fast frontier model with RL · Cursor](https://daily.dev/posts/composer-building-a-fast-frontier-model-with-rl-cursor-5tclsswad) · Hacker News · 0 upvotes · 1 comments --- Tags: [#reinforcement-learning](https://daily.dev/tags/reinforcement-learning), [#ai-assisted-development](https://daily.dev/tags/ai-assisted-development) [View this post on daily.dev](https://daily.dev/posts/improving-composer-through-real-time-rl-cursor-kihj0ypyy) ```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":"Improving Composer through real-time RL · Cursor","url":"https://daily.dev/posts/improving-composer-through-real-time-rl-cursor-kihj0ypyy","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/improving-composer-through-real-time-rl-cursor-kihj0ypyy"},"datePublished":"2026-03-26T16:29:18.669Z","dateModified":"2026-03-26T16:29:56.319Z","description":"Cursor's team describes their 'real-time RL' approach for continuously improving Composer, their AI coding agent. Instead of relying solely on simulated...","image":"https://ptht05hbb1ssoooe.public.blob.vercel-storage.com/assets/blog/og/blog-improving-composer-online-rl-anim-20260324-064314-1200-optim.gif","thumbnailUrl":"https://ptht05hbb1ssoooe.public.blob.vercel-storage.com/assets/blog/og/blog-improving-composer-online-rl-anim-20260324-064314-1200-optim.gif","isAccessibleForFree":true,"articleSection":"Cursor","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":"Cursor","logo":"https://media.daily.dev/image/upload/s--ypWhEpGj--/f_auto/v1752567145/logos/cursor","url":"https://daily.dev/sources/cursor"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/improving-composer-through-real-time-rl-cursor-kihj0ypyy","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"reinforcement-learning,ai-assisted-development","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Cursor","item":"https://daily.dev/sources/cursor"},{"@type":"ListItem","position":3,"name":"Improving Composer through real-time RL · Cursor"}]} ```