Ahoy: LLMs Enacting Multiagent Interaction Protocols
This work addresses the challenge of creating programming-free intelligent agents that can flexibly enact multiple interaction protocols, combining declarative protocols with LLMs for improved knowledge engineering.
Ahoy enables LLM agents to dynamically select and enact declarative interaction protocols without specialized training, achieving correct and intelligent multi-protocol enactment, including concurrent protocols, to fulfill user goals.
An interaction protocol formalizes how the agents in a multiagent system interact, which facilitates implementing agents. Existing approaches yield agent implementations specific to the selected protocols. How can we engineer intelligent agents that can enact protocols but are programming-free? Our contribution, Ahoy, addresses this question by creating LLM agents that dynamically select and enact declarative protocols to achieve user goals. We demonstrate that an \ahoy agent can correctly and intelligently enact multiple protocols - concurrently if appropriate to the user goal - without specialized training. Ahoy's significance lies in that it brings together declarative protocols and LLMs, both approaches that promise improved knowledge engineering for agents.