Embodied LLM Agents Learn to Cooperate in Organized Teams

arXiv:2403.12482v1 Announce Type: cross
Abstract: Large Language Models (LLMs) have emerged as integral tools for reasoning, planning, and decision-making, drawing upon their extensive world knowledge and proficiency in language-related tasks. LLMs thus hold tremendous potential for natural language interaction within multi-agent systems to foster cooperation. However, LLM agents tend to over-report and comply with any instruction, which may result in information redundancy and confusion in multi-agent cooperation. Inspired by human organizations, this paper introduces a framework that imposes prompt-based organization …

abstract agent agents arxiv cs.ai cs.cl cs.cy cs.ma decision embodied however integral knowledge language language models large language large language models learn llm llms making multi-agent natural natural language planning reasoning report systems tasks teams tools type world