发表机构
Pasargad Institute for Advanced Innovative Solutions; Iran University of Science and Technology（帕萨尔加德先进创新解决方案研究所; 伊朗科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对多智能体LLM缺乏社会智能与协调机制的问题，提出EPLA神经符号架构，通过符号保护器控制动作执行，并用认知概率八卦模型形式化认知层，以增强协调能力。
AI 中文摘要
多智能体大语言模型（LLMs）在应用人工智能中已变得无处不在，但其理论基础却令人惊讶地研究不足。通过多智能体系统理论的视角审视，多个缺陷浮现出来：缺乏社会智能、智能体之间缺乏协调机制、未知的涌现行为，以及受自然语言限制的智能体间交互。我们解决了其中两个缺陷：社会行为的缺失和智能体间协调机制的缺乏。我们引入了认知概率语言智能体（EPLA），一种用于不确定性下多智能体协调的神经符号架构。符号保护器提供结构化的诊断反馈。LLM生成类型化动作，保护器根据权威符号状态控制其执行。我们在一个八卦测试平台中通过认知概率八卦模型形式化认知层，该模型将基于视图的呼叫历史与智能体索引的概率权重相结合。我们认为，实现这样的形式化可以解决智能体LLM的缺陷。
英文摘要
Multi-agent large language models (LLMs) have become ubiquitous in applied AI, yet their theoretical foundations remain surprisingly understudied. Viewed through the lens of multi-agent systems theory, several shortcomings come to light: a lack of social intelligence, the absence of coordination mechanisms among agents, unknown emergent behavior, and interactions between agents that are bounded by natural language. We address two of these gaps: the absence of social behavior and the lack of mechanisms for inter-agent coordination. We introduce Epistemic Probabilistic Language Agents (EPLA), a neuro-symbolic architecture for multi-agent coordination under uncertainty. A Symbolic Guard provides structured diagnostic feedback. The LLM generates typed actions, and the Guard controls their execution against an authoritative symbolic state. We formalize the epistemic layer in a gossip testbed through epistemic lottery gossip models, which combine view-based call histories with agent-indexed probability weights. We argue that implementing such a formalism can address shortcomings of agentic LLMs.
