MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning
This addresses the need for more robust and diverse problem-solving in multi-agent systems, though it appears incremental as it builds on existing collaborative reasoning approaches.
The paper tackles the problem of homogeneous agent behaviors and lack of reflective capabilities in collaborative reasoning by proposing MAPS, a framework that assigns distinct personality traits to agents and uses a Critic agent for iterative refinement, resulting in strong performance across three benchmarks.
Collaborative reasoning with multiple agents offers the potential for more robust and diverse problem-solving. However, existing approaches often suffer from homogeneous agent behaviors and lack of reflective and rethinking capabilities. We propose Multi-Agent Personality Shaping (MAPS), a novel framework that enhances reasoning through agent diversity and internal critique. Inspired by the Big Five personality theory, MAPS assigns distinct personality traits to individual agents, shaping their reasoning styles and promoting heterogeneous collaboration. To enable deeper and more adaptive reasoning, MAPS introduces a Critic agent that reflects on intermediate outputs, revisits flawed steps, and guides iterative refinement. This integration of personality-driven agent design and structured collaboration improves both reasoning depth and flexibility. Empirical evaluations across three benchmarks demonstrate the strong performance of MAPS, with further analysis confirming its generalizability across different large language models and validating the benefits of multi-agent collaboration.