让多个智能体各具性格，协作推理更深入灵活。
MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning
- 给每个智能体分配不同人格特质，实现多样化推理风格。
- 引入评论者智能体，可回溯错误步骤并迭代优化结果。
- 适用于提升大模型协作能力，尤其适合复杂推理任务。
多智能体协作推理有望带来更鲁棒、多元的问题解决能力。然而，现有方法常因智能体行为同质化且缺乏反思与重思能力而受限。本文提出多智能体人格塑造框架（MAPS），通过人格驱动的多样性设计和内部批判机制增强推理深度。受五大性格特质理论启发，MAPS为各智能体赋予独特人格，塑造差异化的推理风格，促进异质协作。为实现更深层、自适应的推理，引入评论者（Critic）智能体，对中间输出进行反思，回溯错误步骤并引导迭代修正。该框架融合人格化设计与结构化协作，在三个基准测试中表现优异，进一步分析证实其在不同大语言模型上的泛化能力，并验证了多智能体协作的优势。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。