让个人大模型间像人一样高效协商，支持大规模稳定通信。
LLM-X: A Scalable Negotiation-Oriented Exchange for Communication Among Personal LLM Agents
- 设计了基于主题路由的跨代理通信架构，支持结构化对话
- 实测12个代理在12小时运行中延迟可控，政策越严响应越慢
- 适合研究多智能体协作或个性化AI服务的开发者
我们提出个人大模型交换系统（LLM-X），一个可扩展的协商导向环境，支持代表个体用户的个人代理（大模型）之间直接、结构化的通信。与聚焦工具调用的现有协议不同，LLM-X引入消息总线和路由基础架构，实现大模型间的协调，并保证模式有效性与策略执行。贡献包括：(1) 包含联邦网关、基于主题的路由和策略执行的架构；(2) 支持能力协商与合同网络式协作的类型化消息协议；(3) 首次对大规模大模型多智能体协商进行实证评估。实验涵盖5、9、12个代理，在低、中、高三种协商策略下，分别测试分钟级和2小时、12小时的长时负载。结果表明，更严格的策略虽提升鲁棒性与公平性，但增加延迟和消息量。长时间运行验证了LLM-X在持续负载下的稳定性，延迟漂移保持在可控范围。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。