HARBOR: Exploring Persona Dynamics in Multi-Agent Competition

TL;DR

This paper introduces HARBOR, a platform for studying how personas influence agent strategies and profiling in competitive auctions, revealing insights into multi-agent behavior and strategic advantage using large language models.

Contribution

The work extends auction scenarios with realistic persona and memory modeling, enabling analysis of behavior, profiling, and strategic advantages in multi-agent competition.

Findings

Persona significantly affects agent bidding behavior

Agents can profile competitors to improve strategies

HARBOR provides a platform for multi-agent competitive analysis

Abstract

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.