Can LLM-Augmented autonomous agents cooperate?, An evaluation of their cooperative capabilities through Melting Pot

arXiv:2403.11381v1 Announce Type: cross
Abstract: As the field of AI continues to evolve, a significant dimension of this progression is the development of Large Language Models and their potential to enhance multi-agent artificial intelligence systems. This paper explores the cooperative capabilities of Large Language Model-augmented Autonomous Agents (LAAs) using the well-known Meltin Pot environments along with reference models such as GPT4 and GPT3.5. Preliminary results suggest that while these agents demonstrate a propensity for cooperation, they still struggle with effective …

abstract agent agents artificial artificial intelligence arxiv autonomous autonomous agents capabilities cs.ai cs.cl development evaluation intelligence language language model language models large language large language model large language models llm multi-agent paper systems through type