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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mosquera, Manuel, Pinzon, Juan Sebastian, Rios, Manuel, Fonseca, Yesid, Giraldo, Luis Felipe, Quijano, Nicanor, Manrique, Ruben
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910494929977344
author Mosquera, Manuel
Pinzon, Juan Sebastian
Rios, Manuel
Fonseca, Yesid
Giraldo, Luis Felipe
Quijano, Nicanor
Manrique, Ruben
author_facet Mosquera, Manuel
Pinzon, Juan Sebastian
Rios, Manuel
Fonseca, Yesid
Giraldo, Luis Felipe
Quijano, Nicanor
Manrique, Ruben
contents 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 collaboration in given environments, emphasizing the need for more robust architectures. The study's contributions include an abstraction layer to adapt Melting Pot game scenarios for LLMs, the implementation of a reusable architecture for LLM-mediated agent development - which includes short and long-term memories and different cognitive modules, and the evaluation of cooperation capabilities using a set of metrics tied to the Melting Pot's "Commons Harvest" game. The paper closes, by discussing the limitations of the current architectural framework and the potential of a new set of modules that fosters better cooperation among LAAs.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11381
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Can LLM-Augmented autonomous agents cooperate?, An evaluation of their cooperative capabilities through Melting Pot
Mosquera, Manuel
Pinzon, Juan Sebastian
Rios, Manuel
Fonseca, Yesid
Giraldo, Luis Felipe
Quijano, Nicanor
Manrique, Ruben
Artificial Intelligence
Computation and Language
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 collaboration in given environments, emphasizing the need for more robust architectures. The study's contributions include an abstraction layer to adapt Melting Pot game scenarios for LLMs, the implementation of a reusable architecture for LLM-mediated agent development - which includes short and long-term memories and different cognitive modules, and the evaluation of cooperation capabilities using a set of metrics tied to the Melting Pot's "Commons Harvest" game. The paper closes, by discussing the limitations of the current architectural framework and the potential of a new set of modules that fosters better cooperation among LAAs.
title Can LLM-Augmented autonomous agents cooperate?, An evaluation of their cooperative capabilities through Melting Pot
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2403.11381