Our research question: can we make a channel that helps real-time collaboration for AI coding work? We leveraged Conflict-free Replicated Data Type called CRDT for seamless communication. We call this channel a Room.</p>\n","updatedAt":"2026-08-26T15:14:19.248Z","author":{"_id":"64105805928400b416439f10","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64105805928400b416439f10/i0jFLo47RTDeNl26hiR9y.jpeg","fullname":"Seonglae Cho","name":"seonglae","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":6,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.937335729598999},"editors":["seonglae"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/64105805928400b416439f10/i0jFLo47RTDeNl26hiR9y.jpeg"],"reactions":[],"isReport":false}},{"id":"6a8f74e9d720ca2e6527ae96","author":{"_id":"64105805928400b416439f10","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64105805928400b416439f10/i0jFLo47RTDeNl26hiR9y.jpeg","fullname":"Seonglae Cho","name":"seonglae","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":6,"isUserFollowing":false},"createdAt":"2026-08-26T23:21:13.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"https://cdn-uploads.huggingface.co/production/uploads/64105805928400b416439f10/eEbOLm5D6Tked8Wg40HN0.mp4\n","html":"<p><video src=\"https://cdn-uploads.huggingface.co/production/uploads/64105805928400b416439f10/eEbOLm5D6Tked8Wg40HN0.mp4\" controls=\"\" class=\"max-w-full!\"></video></p>\n","updatedAt":"2026-08-26T23:21:13.322Z","author":{"_id":"64105805928400b416439f10","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64105805928400b416439f10/i0jFLo47RTDeNl26hiR9y.jpeg","fullname":"Seonglae Cho","name":"seonglae","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":6,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.42698583006858826},"editors":["seonglae"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/64105805928400b416439f10/i0jFLo47RTDeNl26hiR9y.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.23740","authors":[{"_id":"6a8efcb72c24e8c5fab326a7","user":{"_id":"64105805928400b416439f10","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64105805928400b416439f10/i0jFLo47RTDeNl26hiR9y.jpeg","isPro":false,"fullname":"Seonglae Cho","user":"seonglae","type":"user","name":"seonglae"},"name":"Seonglae Cho","status":"claimed_verified","statusLastChangedAt":"2026-08-26T16:45:04.647Z","hidden":false},{"_id":"6a8efcb72c24e8c5fab326a8","name":"Donghyun Lee","hidden":false}],"publishedAt":"2026-08-24T00:00:00.000Z","submittedOnDailyAt":"2026-08-26T00:00:00.000Z","title":"AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace","submittedOnDailyBy":{"_id":"64105805928400b416439f10","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64105805928400b416439f10/i0jFLo47RTDeNl26hiR9y.jpeg","isPro":false,"fullname":"Seonglae Cho","user":"seonglae","type":"user","name":"seonglae"},"summary":"Concurrent multi-agent coding promises division of labor across modules, robustness through redundancy, and parallel exploration at the natural granularity of multi-file projects. Realtime collaborative editing protocols solve this coordination problem for human teams via Conflict-free Replicated Data Types (CRDTs), but the LLMs underneath generate one token at a time and existing multi-agent coding systems inherit this serial limit: they either sequence agents through phase handoffs or pool independent samples without coordination, and a single agent abandons up to half of hard tasks with a one-file stub-and-exit. AgentRoom is a realtime collaborative editing protocol for concurrent coding agents. Its runtime layer exposes file-level claim, status, and broadcast as MCP tools on a CRDT-merged shared filesystem. Five frontier coding-CLI models ran four backend coding tasks, with cross-language checks in Python DevBench and Rust+axum. For CLI-stable models, AgentRoom with 2 agents abandons fewer tasks than Solo and has less run-to-run variation. At matched-compute, one positive mean LLM-judge contrast puts AgentRoom over parallel-merge. The other contrast, a bundle probe, puts full AgentRoom above each partial case: an ordering rather than a percentage split. Coordination, not parallelism or CRDT-merge, bears the load.","upvotes":4,"discussionId":"6a8efcb82c24e8c5fab326a9","projectPage":"https://seongland.com/article/agentroom","ai_summary":"AgentRoom enables concurrent multi-agent coding through real-time collaborative editing and shared filesystem coordination, reducing task abandonment and improving consistency compared to solo or uncoordinated parallel approaches.","ai_keywords":["CRDTs","multi-agent coding","AgentRoom","MCP tools","shared filesystem","LLM-judge"],"ai_summary_model":"thinkingmachines/Inkling-Small"},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"64105805928400b416439f10","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64105805928400b416439f10/i0jFLo47RTDeNl26hiR9y.jpeg","isPro":false,"fullname":"Seonglae Cho","user":"seonglae","type":"user"},{"_id":"68383cfda2d6f83cf1ee88a0","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/mGNmuxzz1zaPZyMQFCde6.jpeg","isPro":false,"fullname":"Seonglae Cho","user":"seonglae-holistic","type":"user"},{"_id":"631e14ac473a6825f285e89d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/631e14ac473a6825f285e89d/K-6QnoeGLg8XFvbTMMdqA.jpeg","isPro":false,"fullname":"Yury Panikov","user":"panikov","type":"user"},{"_id":"63ac5701c21e60a3e9b58aa7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63ac5701c21e60a3e9b58aa7/g6EX7diOpuA94R2ab-rZC.png","isPro":true,"fullname":"Dipankar Sarkar","user":"dipankarsarkar","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.23740.md","query":{}}">
AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace
Abstract
AgentRoom enables concurrent multi-agent coding through real-time collaborative editing and shared filesystem coordination, reducing task abandonment and improving consistency compared to solo or uncoordinated parallel approaches.
Concurrent multi-agent coding promises division of labor across modules, robustness through redundancy, and parallel exploration at the natural granularity of multi-file projects. Realtime collaborative editing protocols solve this coordination problem for human teams via Conflict-free Replicated Data Types (CRDTs), but the LLMs underneath generate one token at a time and existing multi-agent coding systems inherit this serial limit: they either sequence agents through phase handoffs or pool independent samples without coordination, and a single agent abandons up to half of hard tasks with a one-file stub-and-exit. AgentRoom is a realtime collaborative editing protocol for concurrent coding agents. Its runtime layer exposes file-level claim, status, and broadcast as MCP tools on a CRDT-merged shared filesystem. Five frontier coding-CLI models ran four backend coding tasks, with cross-language checks in Python DevBench and Rust+axum. For CLI-stable models, AgentRoom with 2 agents abandons fewer tasks than Solo and has less run-to-run variation. At matched-compute, one positive mean LLM-judge contrast puts AgentRoom over parallel-merge. The other contrast, a bundle probe, puts full AgentRoom above each partial case: an ordering rather than a percentage split. Coordination, not parallelism or CRDT-merge, bears the load.
Community
Our research question: can we make a channel that helps real-time collaboration for AI coding work? We leveraged Conflict-free Replicated Data Type called CRDT for seamless communication. We call this channel a Room.
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2608.23740 in a model README.md to link it from this page.
Cite arxiv.org/abs/2608.23740 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2608.23740 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.