A Scalable Communication Protocol for Networks of Large Language Models

TL;DR

This work tackles the challenge of scalable, heterogeneous communication in networks of LLM-powered agents by introducing Agora, a meta protocol that combines structured protocol documents with natural-language interactions to balance versatility, efficiency, and portability. Through two demos—a two-agent weather forecast exchange and a 100-agent network—they demonstrate autonomous negotiation, protocol implementation, and emergent, self-organizing workflows, accompanied by substantial cost savings compared with natural-language-only communication. The key contribution is the Protocol Document (PD) concept and the Layer Zero positioning of Agora, enabling decentralized, flexible, and scalable collaboration across diverse technologies. The results suggest that LLM-driven agent networks can autonomously evolve efficient protocols, reducing human intervention and expanding the practical reach of large-scale AI collaboration.

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.

Figures (6)

• Figure 1: The Trilemma and how our solution (Agora) balances efficiency, portability and versatility.
• Figure 2: How Agora fits into a standard communication protocol stack.
• Figure 3: How a protocol document is negotiated between LLM-powered agents (left) and used for future efficient communications.
• Figure 4: Illustration of how in an Agora network with $100$ agents (left; for clarity, only the relevant sub-network is displayed), an emergent protocol for food delivery emerges (right).
• Figure 5: Summary of the efficiency of Agora for the demo with 100 agents.