发表机构
Holistic AI; University of California, Berkeley(整体人工智能公司; 加州大学伯克利分校)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
AgentRoom是基于CRDT的并发多智能体编码协议,通过协调机制减少任务放弃率,在计算量匹配下优于单独运行和并行合并,为多智能体编码提供更优方案。
AI 中文摘要
并发多智能体编码有望实现跨模块的分工、通过冗余获得鲁棒性,并以多文件项目的自然粒度进行并行探索。实时协同编辑协议通过无冲突复制数据类型(Conflict-free Replicated Data Types,CRDT)解决了人类团队的协调问题,但底层的大型语言模型(LLM)一次仅生成一个token,而现有的多智能体编码系统继承了这种串行限制:它们要么通过阶段交接对智能体进行排序,要么汇集独立的样本而不进行协调,单个智能体在遇到单文件存根后退出时会放弃多达一半的困难任务。AgentRoom是一种用于并发编码智能体的实时协同编辑协议,其运行时层在CRDT合并的共享文件系统上公开文件级别的声明、状态和广播作为MCP工具。五个前沿编码CLI模型运行了四个后端编码任务,其中包括Python DevBench和Rust+axum的跨语言检查。对于CLI稳定的模型,使用2个智能体的AgentRoom比单独运行(Solo)放弃的任务更少,且运行间差异更小;在计算量匹配的情况下,一项积极的平均LLM评判对比显示AgentRoom优于并行合并(parallel-merge),另一项捆绑探测对比显示完整的AgentRoom优于每种部分情况,其优势体现在排序而非百分比拆分上,协调而非并行性或CRDT合并承担了主要作用。
英文摘要
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.