arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.17152cs.CLcs.AI
收藏

多智能体辩论中的动态角色分配

Dynamic Role Assignment for Multi-Agent Debate

New York University(纽约大学);Amazon AGI(亚马逊人工智慧)

Miao Zhang, Junsik Kim, Siyuan Xiang, Jian Gao, Cheng Cao

AI总结:

本文提出动态角色分配框架,通过元辩论选择适合的智能体,提升多代理辩论系统的性能。

摘要:

多智能体大语言模型(LLM)和视觉语言模型(VLM)辩论系统采用专门的角色进行复杂问题解决,但模型专门化并未被用来决定哪个模型应填充哪个角色。我们提出了动态角色分配,一种在实际辩论前运行元辩论以选择合适代理的框架。元辩论分为两个阶段:(1)提案阶段,候选者提供角色定制的论点;(2)同行评审阶段,提案通过数据和角色特定的标准进行评分,以选择最适合每个职位的代理。我们在LLM问题解决基准上评估了我们的方法。在现有辩论系统之上应用我们的方法,我们的方法在任务和特定分配方面,比统一分配(用相同模型填充所有角色)高出多达74.8%,比随机分配(不考虑模型适合性的分配)高出多达29.7%。这项工作为多代理系统设计建立了一种新范式,从静态代理部署转向动态和能力感知的选择。

英文摘要:

Multi-agent large language model (LLM) and vision-language model (VLM) debate systems employ specialized roles for complex problem-solving, yet model specializations are not leveraged to decide which model should fill which role. We propose dynamic role assignment, a framework that runs a Meta-Debate to select suitable agents before the actual debate. The meta-debate has two stages: (1) proposal, where candidates provide role-tailored arguments, and (2) peer review, where proposals are scored with data and role-specific criteria to choose the best agent for each position. We evaluate our method on LLM problem solving benchmarks. Applied on top of existing debate systems, our approach consistently outperforms uniform assignments (filling all roles with the same model) by up to 74.8% and random assignments (assigning models to roles without considering their suitability) by up to 29.7%, depending on the task and the specific assignment. This work establishes a new paradigm for multi-agent system design, shifting from static agent deployment to dynamic and capability-aware selection.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑