What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems 事件

What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems arXiv:2606.05304v1 Announce Type: new Abstract: Multi-agent systems (MAS) built on large language models are typically organized around roles, pipelines, and turn schedules, while the content that agents pass to one another is often left as unconstrained natural language. However, this free-form communication can rapidly inflate token usage, consume the shared context window, and ultimately affect both system p