HARBOR: Exploring Persona Dynamics in Multi-Agent Competition
This work addresses the challenge of persona dynamics in multi-agent systems for researchers in AI and agent-based modeling, but it is incremental as it extends classic auction scenarios with persona-based analysis.
The study tackled the problem of understanding LLM agent success in competitive multi-agent auctions by investigating how personas influence behavior, competitor profiling, and strategic advantages, using a testbed called HARBOR to analyze agent interactions in a realistic house-bidding environment.
We investigate factors contributing to LLM agents' success in competitive multi-agent environments, using auctions as a testbed where agents bid to maximize profit. The agents are equipped with bidding domain knowledge, distinct personas that reflect item preferences, and a memory of auction history. Our work extends the classic auction scenario by creating a realistic environment where multiple agents bid on houses, weighing aspects such as size, location, and budget to secure the most desirable homes at the lowest prices. Particularly, we investigate three key questions: (a) How does a persona influence an agent's behavior in a competitive setting? (b) Can an agent effectively profile its competitors' behavior during auctions? (c) How can persona profiling be leveraged to create an advantage using strategies such as theory of mind? Through a series of experiments, we analyze the behaviors of LLM agents and shed light on new findings. Our testbed, called HARBOR, offers a valuable platform for deepening our understanding of multi-agent workflows in competitive environments.