AI智能体协作的收敛理论：局部工作与全局进展
原标题：Local Work, Global Progress: A Convergence Theory of AI Agent Collaboration
AI 摘要
该论文将多个LLM智能体的协作问题形式化为块优化问题：每个智能体在局部目标加上跨块影响修正的引导下搜索共享解的一部分，协调器用全局目标验证提案并合并不冲突的提案，作者证明了线性收敛（误差下限在修正精确时消失）。实验用GPT-OSS-120B智能体在机器人路径规划任务上验证，三智能体团队每次都能找到无碰撞方案，六智能体团队搜索速度中位数约为单智能体的两倍，合并已验证的最佳提案组合还能再缩短约30%搜索时间。
正文节选
Local Work, Global Progress: A Convergence Theory of AI Agent Collaboration Abstract. Teams of large language model (LLM) agents are increasingly applied to complex tasks, but their collaboration protocols are mostly designed empirically, without convergence guarantees. We formalize collaborative problem solving as block optimization: each agent improves one part of a shared solution, guided by its local objective plus a correction for how its changes affect the other parts. A coordinator checks