摘要：

在多智能体博弈仿真中, 大语言模型(LLM)的性能已经被广泛研究, 但其在模糊任务目标或不确定性环境中引导多智能体合作的决策能力往往出现"失灵"现象。针对这一问题, 提出一种基于分布式贝叶斯推断的多层级协同决策框架。该框架集成了决策、互评、监管三大功能模块, 利用多个LLM进行协同决策, 并在空间囚徒困境博弈中进行了实验验证。实验结果表明, 该框架有效克服了LLM在模糊任务环境下的决策瓶颈, 成功促进了多智能体合作行为的涌现。此外, 通过对不同实验场景下模型决策能力的量化评估, 发现模型的决策误差与模型规模不呈线性关系。在模糊任务指令下, LLaMA3(70×10⁹)模型的决策误差较LLaMA3(8×10⁹)模型高出16.6%, 较LLaMA2(7×10⁹)模型高出7.2%, 表明在更复杂的环境中, 单纯依赖模型规模的扩大未能显著提升决策性能。相反, LLM协同决策在提升决策一致性和有效性方面显示出显著优势。这些结果揭示了多模型协同在复杂决策环境中的关键作用, 并为未来在不确定性任务下的智能体系统设计提供了重要参考。

关键词: 大语言模型, 多智能体仿真, 空间囚徒困境博弈, 分布式贝叶斯推断, 多层级协同决策框架

Abstract:

In multi-agent game simulations, the performance of Large Language Model (LLM) has been widely studied; however, their decision-making ability to guide multi-agent cooperation in fuzzy task objectives or uncertain environments is often unreliable. To address this issue, a multi-level collaborative decision-making framework based on distributed Bayesian inferences is proposed. This framework integrates three major functional modules: decision making, peer evaluation, and supervision. It utilizes multiple LLM for collaborative decision making and has been experimentally validated in a spatial prisoner's dilemma game. The experimental results show that the framework effectively overcomes the decision-making bottleneck of LLM in fuzzy task environments and successfully promotes the emergence of multi-agent cooperative behavior. Additionally, a quantitative evaluation of the model's decision-making ability in different experimental scenarios reveals that the decision error of the model is not linearly related to the model size. Under fuzzy task instructions, the decision error of the LLaMA3 (70×10⁹) model is 16.6% higher than that of the LLaMA3 (8×10⁹) model and 7.2% higher than that of the LLaMA2 (7×10⁹) model. This indicates that in more complex environments, relying solely on the expansion of the model size does not significantly improve the decision-making performance. By contrast, LLM collaborative decision making has shown significant advantages in improving decision consistency and effectiveness. These results reveal the crucial role of multi-model collaboration in complex decision-making environments and provide important references for the future design of intelligent agent systems for uncertain tasks.

Key words: Large Language Models (LLM), multi-agent simulation, spatial prisoner's dilemma game, distributed Bayesian inference, multi-level collaborative decision-making framework