A Scalable Communication Protocol for Networks of Large Language Models

Samuele Marro, Emanuele La Malfa, Jesse Wright, Guohao Li, Nigel Shadbolt, Michael J. Wooldridge, Philip Torr

Keywords: llm, multi-agent systems, protocol, negotiation, collaboration

TL;DR: A meta protocol for communication between heterogeneous LLM-powered agents.

Abstract:

Communication is a prerequisite for collaboration. When scaling networks of AI-powered agents, communication must be versatile, efficient, and portable. These requisites, which we refer to as the Agent Communication Trilemma, are hard to achieve in large networks of agents. We introduce Agora, a meta protocol that leverages existing communication standards to make LLM-powered agents solve complex problems efficiently. In Agora, agents typically use standardised routines for frequent communications, natural language for rare communications, and LLM-written routines for everything in between. Agora sidesteps the Agent Communication Trilemma and robustly handles changes in interfaces and members, allowing unprecedented scalability with full decentralisation and minimal involvement of human beings. On large Agora networks, we observe the emergence of self-organising, fully automated protocols that achieve complex goals without human intervention.

Primary Area: foundation or frontier models, including LLMs

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 12280