多智能体推理的自适应专家群

中文摘要 AI 辅助

多智能体系统将具有不同角色的语言模型智能体聚集在一起，以提出、审查和优化解决方案。每个智能体的响应取决于其模型的能力、其系统提示符定义的推理策略以及其输入上下文中的信息。现有框架通常通过改变上下文来适应通信，同时保持个体提示符固定，即使问题需要不同的技能。我们研究智能体的初始响应是否能识别出更适合当前问题的策略，并引导其向其他智能体转移。为解决这一问题，我们引入了SAGE（自适应专家群），这是一个无需训练的框架，利用答案一致性、前缀一致性和互惠同行评审来选择策略提供者。SAGE将所选提供者的推理策略转移给其他智能体，同时保留其原始角色。这种转移仅使用智能体原有的系统提示符，无需访问问题或生成的解决方案。策略适应后，智能体通过动态稀疏有向无环图交换响应，该图将信息从得分较高的智能体路由到得分较低的智能体。在多个智能体骨干和推理基准上的实验表明，SAGE相比评估的基线实现了更高的平均准确率。我们的代码可在该https URL获取。

英文摘要

Multi-agent systems bring together language model agents with different roles to propose, review, and refine solutions. Each agent's response depends on its model's capabilities, the reasoning strategy defined by its system prompt, and the information in its input context. Existing frameworks often adapt communication by changing this context while leaving individual prompts fixed, even when a problem calls for different skills. We study whether agents' initial responses can identify a strategy better suited to the current problem and guide its transfer to other agents. To address this, we introduce SAGE (Self-Adapting Group of Experts), a training-free framework that uses answer agreement, prefix consistency, and reciprocal peer review to select a strategy donor. SAGE transfers the selected donor's reasoning strategy to the other agents while preserving their original roles. This transfer uses only the agents' original system prompts, without access to the problem or generated solutions. After strategy adaptation, agents exchange responses through a dynamic, sparse directed acyclic graph that routes information from higher-scoring agents to lower-scoring agents. Experiments across multiple agent backbones and reasoning benchmarks show that SAGE achieves higher average accuracy than the evaluated baselines. Our code is available at https://github.com/atifquamar07/sage.

发表机构

• Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
• Michigan State University（密歇根州立大学）
• RIKEN AIP（日本理化学研究所人工智能中心）

机构由 AI 辅助整理，请以论文原文为准。