Bayesian Partner Modelling enables Adaptive Replanning for LLM Coordination

2026-08-18

AI Summary

为解决多代理LLM系统中队友策略变化导致的协作问题，提出BayesBeliefAgent，结合贝叶斯追踪模块与层次化LLM规划器，仅在必要时中断当前技能以提高适应性和效率。

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 Because agents execute multi-step or temporally extended skills, they frequently continue executing outdated plans long after public evidence shows that a partner has changed its skill.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 shift but slow to act-or replan indiscriminately. We introduce BayesBeliefAgent, which pairs a hierarchical LLM planner with a Bayesian tracking module. Rather than replanning constantly, our agent interrupts its current skill only when a partner's actions directly contradict the inferred skill. Beyond standard reward, we evaluate performance using replanning efficiency and the belief-action gap: the fraction of total decisions where an agent with a correct partner estimate executes a non-complementary skill. Across benchmark Overcooked environments, contradiction-conditioned control drastically narrows this belief-action gap while requiring an order of magnitude fewer replans than heuristic methods

Problem

• Multi-agent Large Language Model
• collaboration
• strategy shift
• outdated plans
• partner tracking

Innovation

• Bayesian Partner Modelling
• Adaptive Replanning
• Hierarchical LLM Planner