TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination
TeamTR: 用于多智能体大语言模型协调的信赖区域微调
机构 * Department of Electrical \& Computer Engineering, University of Arizona ； Engineering College, Soochow University ； INSAIT, Sofia University "St. Kliment Ohridski" ； Department of Electrical ； Computer Engineering, Stony Brook University
专题命中 规划控制 ：occupancy(abstract)
AI总结 本文提出TeamTR，通过信赖区域框架在每个组件更新后重采样轨迹并控制每个智能体的发散度，解决多智能体系统中因上下文分布变化导致的性能下降问题，实验表明其在协调回归抑制和组件替换支持方面优于单智能体和序列基线。
Comments 9pages, Accepted at ICML2026
