Guardado en:
Detalles Bibliográficos
Autores principales: Suprabha, Hima Jacob Leven, Nagesh, Laxmi Nag Laxminarayan, Nair, Ajith, Selvaster, Alvin Reuben Amal, Khan, Ayan, Damarla, Raghuram, Samuel, Sanju Hannah, Perumal, Sreenithi Saravana, Puech, Titouan, Marella, Venkataramireddy, Sonar, Vishal, Suglia, Alessandro, Lemon, Oliver
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2510.03153
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914072741543936
author Suprabha, Hima Jacob Leven
Nagesh, Laxmi Nag Laxminarayan
Nair, Ajith
Selvaster, Alvin Reuben Amal
Khan, Ayan
Damarla, Raghuram
Samuel, Sanju Hannah
Perumal, Sreenithi Saravana
Puech, Titouan
Marella, Venkataramireddy
Sonar, Vishal
Suglia, Alessandro
Lemon, Oliver
author_facet Suprabha, Hima Jacob Leven
Nagesh, Laxmi Nag Laxminarayan
Nair, Ajith
Selvaster, Alvin Reuben Amal
Khan, Ayan
Damarla, Raghuram
Samuel, Sanju Hannah
Perumal, Sreenithi Saravana
Puech, Titouan
Marella, Venkataramireddy
Sonar, Vishal
Suglia, Alessandro
Lemon, Oliver
contents The integration of Large Language Models (LLMs) into multiagent systems has opened new possibilities for collaborative reasoning and cooperation with AI agents. This paper explores different prompting methods and evaluates their effectiveness in enhancing agent collaborative behaviour and decision-making. We enhance CoELA, a framework designed for building Collaborative Embodied Agents that leverage LLMs for multi-agent communication, reasoning, and task coordination in shared virtual spaces. Through systematic experimentation, we examine different LLMs and prompt engineering strategies to identify optimised combinations that maximise collaboration performance. Furthermore, we extend our research by integrating speech capabilities, enabling seamless collaborative voice-based interactions. Our findings highlight the effectiveness of prompt optimisation in enhancing collaborative agent performance; for example, our best combination improved the efficiency of the system running with Gemma3 by 22% compared to the original CoELA system. In addition, the speech integration provides a more engaging user interface for iterative system development and demonstrations.
format Preprint
id arxiv_https___arxiv_org_abs_2510_03153
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Cooperation in Collaborative Embodied AI
Suprabha, Hima Jacob Leven
Nagesh, Laxmi Nag Laxminarayan
Nair, Ajith
Selvaster, Alvin Reuben Amal
Khan, Ayan
Damarla, Raghuram
Samuel, Sanju Hannah
Perumal, Sreenithi Saravana
Puech, Titouan
Marella, Venkataramireddy
Sonar, Vishal
Suglia, Alessandro
Lemon, Oliver
Artificial Intelligence
Multiagent Systems
Robotics
The integration of Large Language Models (LLMs) into multiagent systems has opened new possibilities for collaborative reasoning and cooperation with AI agents. This paper explores different prompting methods and evaluates their effectiveness in enhancing agent collaborative behaviour and decision-making. We enhance CoELA, a framework designed for building Collaborative Embodied Agents that leverage LLMs for multi-agent communication, reasoning, and task coordination in shared virtual spaces. Through systematic experimentation, we examine different LLMs and prompt engineering strategies to identify optimised combinations that maximise collaboration performance. Furthermore, we extend our research by integrating speech capabilities, enabling seamless collaborative voice-based interactions. Our findings highlight the effectiveness of prompt optimisation in enhancing collaborative agent performance; for example, our best combination improved the efficiency of the system running with Gemma3 by 22% compared to the original CoELA system. In addition, the speech integration provides a more engaging user interface for iterative system development and demonstrations.
title Improving Cooperation in Collaborative Embodied AI
topic Artificial Intelligence
Multiagent Systems
Robotics
url https://arxiv.org/abs/2510.03153