通过信念校准选择最优协作伙伴，提升复杂NLP任务的稳定共识
Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks
- 基于信念一致性筛选最优协作伙伴，避免无效交互
- 在MATH和MMLU上分别提升2.23%和3.95%准确率
- 适合需要多智能体协同推理的复杂NLP场景
多智能体系统（MAS）通过智能体间协作提升解决复杂自然语言处理（NLP）任务的能力，其中共识寻求是核心机制。然而，现有方法多依赖投票判断共识，忽视系统内部信念的矛盾，导致共识不稳定。同时，这些方法常让智能体与所有其他智能体无差别协作，无法识别最优协作对象，阻碍稳定共识形成。为此，我们提出了一个理论框架，用于选择能最大化共识稳定性的最优协作伙伴。基于该理论，我们提出信念校准共识寻求（BCCS）框架，通过优选协作伙伴并根据系统内部信念校准共识判断，实现更稳定的共识。在MATH和MMLU基准数据集上的实验表明，BCCS在挑战性任务上分别比现有最佳结果提升2.23%和3.95%的准确率。代码与数据已开源。
原文摘要 · Abstract (English)
A multi-agent system (MAS) enhances its capacity to solve complex natural language processing (NLP) tasks through collaboration among multiple agents, where consensus-seeking serves as a fundamental mechanism. However, existing consensus-seeking approaches typically rely on voting mechanisms to judge consensus, overlooking contradictions in system-internal beliefs that destabilize the consensus. Moreover, these methods often involve agents updating their results through indiscriminate collaboration with every other agent. Such uniform interaction fails to identify the optimal collaborators for each agent, hindering the emergence of a stable consensus. To address these challenges, we provide a theoretical framework for selecting optimal collaborators that maximize consensus stability. Based on the theorems, we propose the Belief-Calibrated Consensus Seeking (BCCS) framework to facilitate stable consensus via selecting optimal collaborators and calibrating the consensus judgment by system-internal beliefs. Experimental results on the MATH and MMLU benchmark datasets demonstrate that the proposed BCCS framework outperforms the best existing results by 2.23% and 3.95% of accuracy on challenging tasks, respectively. Our code and data are available at https://github.com/dengwentao99/BCCS.
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。