LLM-X: A Scalable Negotiation-Oriented Exchange for Communication Among Personal LLM Agents

TL;DR

This paper introduces LLM-X, a scalable environment for structured, negotiation-oriented communication among personal LLM agents, enabling multi-agent coordination with policy enforcement and empirical evaluation.

Contribution

It presents an architecture, message protocol, and the first empirical evaluation of multi-agent negotiation among LLMs at scale.

Findings

Stricter policies improve robustness and fairness.

Stricter policies increase latency and message volume.

LLM-X remains stable under sustained load.

Abstract

We propose a personal-LLM exchange (LLM-X), a scalable negotiation-oriented environment that enables direct, structured communication across populations of personal agents (LLMs), each representing an individual user. Unlike existing tool-centric protocols that focus on agent-API interaction, LLM-X introduces a message bus and routing substrate for LLM-to-LLM coordination with guarantees around schema validity and policy enforcement. We contribute: (1) an architecture for LLM-X comprising federated gateways, topic-based routing, and policy enforcement; (2) a typed message protocol supporting capability negotiation and contract-net-style coordination; and (3) the first empirical evaluation of LLM-based multi-agent negotiation at scale. Experiments span 5, 9, and 12 agents, under distinct negotiation policies (Low, Medium, High), and across both short-run (minutes) and long-run (2h, 12h) load conditions. Results highlight clear policy-performance trade-offs: stricter policies improve robustness and fairness but increase latencies and message volume. Extended runs confirm that LLM-X remains stable under sustained load, with bounded latency drift.