PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games

arXiv:2404.17662v1 Announce Type: new
Abstract: Recent advancements in Large Language Models (LLMs) have enhanced the efficacy of agent communication and social interactions. Despite these advancements, building LLM-based agents for reasoning in dynamic environments involving competition and collaboration remains challenging due to the limitations of informed graph-based search methods. We propose PLAYER*, a novel framework based on an anytime sampling-based planner, which utilises sensors and pruners to enable a purely question-driven searching framework for complex reasoning tasks. We also introduce a …

abstract agent agents arxiv building collaboration communication competition cs.cl dynamic environments games graph graph-based interactions language language models large language large language models limitations llm llms multi-agent murder reasoning search social type