Experimenting with Planning and Reasoning in Ad Hoc Teamwork Environments with Large Language Models

Polyana Costa, Pedro Santos, José Boaro, Daniel Moraes, Júlio Duarte, Sergio Colcher

2024

Abstract

Ad Hoc Teamwork environments are dynamic spaces where agents engage in activities, make decisions, and collaborate with teammates without prior coordination or complete knowledge of tasks. To effectively operate in such an environment, an ad hoc agent must be equipped with robust reasoning and planning mechanisms. Since Large Language Models (LLMs) are known for their generalization abilities, this study showcases their application in ad hoc scenarios. By modeling the robot’s actions using LangChain Tools, building a semantic map, and capturing human communication interactions, we tested the LLM reasoning capabilities in three simulated scenarios involving humans and a robot. In each case, after providing contextual information, we build a meta-prompt with the question: ‘How can the Robot help?’. By conducting these tests, this study highlighted the LLM’s ability to infer tasks and craft action plans even in the absence of explicit verbal commands.

Paper Citation

in Harvard Style

Costa P., Santos P., Boaro J., Moraes D., Duarte J. and Colcher S. (2024). Experimenting with Planning and Reasoning in Ad Hoc Teamwork Environments with Large Language Models. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 438-445. DOI: 10.5220/0012472600003636

in Bibtex Style

@conference{icaart24,
author={Polyana Costa and Pedro Santos and José Boaro and Daniel Moraes and Júlio Duarte and Sergio Colcher},
title={Experimenting with Planning and Reasoning in Ad Hoc Teamwork Environments with Large Language Models},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART},
year={2024},
pages={438-445},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012472600003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART
TI - Experimenting with Planning and Reasoning in Ad Hoc Teamwork Environments with Large Language Models
SN - 978-989-758-680-4
AU - Costa P.
AU - Santos P.
AU - Boaro J.
AU - Moraes D.
AU - Duarte J.
AU - Colcher S.
PY - 2024
SP - 438
EP - 445
DO - 10.5220/0012472600003636
PB - SciTePress