返回全部动态
贝叶斯伙伴建模实现LLM协作中的自适应重规划
原标题：Bayesian Partner Modelling enables Adaptive Replanning for LLM Coordination
AI 摘要
arXiv 论文提出 BayesBeliefAgent，将分层 LLM 规划器与贝叶斯跟踪模块结合，用于多智能体协作中的自适应重规划。该方法仅在伙伴行为与推断技能矛盾时中断当前技能，从而缩小信念-行动差距，并在 Overcooked 基准上比启发式方法减少约两个数量级的重规划次数。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
Bayesian Partner Modelling enables Adaptive Replanning for LLM Coordination Abstract Multi-agent Large Language Model (LLM) systems often struggle to collaborate with new teammates whose strategies shift mid-task. Because agents execute multi-step or temporally extended skills, they frequently continue executing outdated plans long after public evidence shows that a partner has changed its skill. Existing methods either treat partner tracking as passive context—leaving the agent aware of the shi
发布时间：2026-08-20 12:00
抓取时间：2026-08-20 12:22
来源机构：arXiv