AgentRoom：基于 CRDT 共享工作区的并发多智能体编码协议

View PDF HTML (experimental)

Abstract:Concurrent multi-agent coding offers a 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 with 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, since 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 varies less from run to run. 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, is the key design choice.

Comments:	Accepted at NeurIPS 2026. 26 pages, 10 figures, 12 tables
Subjects:	Artificial Intelligence (cs.AI); Software Engineering (cs.SE)
Cite as:	arXiv:2608.23740 [cs.AI]
	(or arXiv:2608.23740v2 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2608.23740 arXiv-issued DOI via DataCite

Submission history

From: Seonglae Cho [view email]
[v1] Mon, 24 Aug 2026 18:28:33 UTC (794 KB)
[v2] Thu, 12 Nov 2026 06:51:14 UTC (772 KB)