AI 中文总结
本研究提出符号引导分类法（SGT），通过调节LLM智能体的自主性层级（介于自然语言推理与完全算法执行之间），显著提升分布式多智能体协调性能，确立了自主性调节作为关键设计原则。
AI 中文摘要
大型语言模型（LLMs）越来越多地被部署为多智能体系统中的自主智能体，然而它们可靠执行分布式协调协议的能力仍鲜为人知。尽管AgentsNet（一个用于LLM智能体间分布式协调的基准框架）能够实现这种协调，但赋予完全的推理自主权往往会导致在复杂领域中出现不一致或性能下降的表现。我们假设，通过源自成熟算法的符号引导来调节智能体自主性，可以改善协调效果。为探究这一假设，我们引入了符号引导分类法（Symbolic Guidance Taxonomy，SGT），该分类法刻画了从开放式自然语言推理到完全规定性算法执行的一系列自主性层级，其中间层级提供部分伪代码引导。我们的结果表明，中间自主性层级的表现始终优于无引导的智能体和完全规定性的规范。这些发现将自主性调节确立为基于LLM的分布式协调的一个关键设计原则。
英文摘要
Large language models (LLMs) are increasingly deployed as autonomous agents in multi-agent systems, yet their ability to reliably execute distributed coordination protocols remains poorly understood. While AgentsNet, a benchmark framework for distributed coordination among LLM agents, enables such coordination, granting full reasoning autonomy often leads to inconsistent or degraded performance in complex domains. We hypothesize that coordination can be improved by regulating agent autonomy through symbolic guidance derived from established algorithms. To investigate this, we introduce the \emph{Symbolic Guidance Taxonomy (SGT)}, which characterizes a spectrum of autonomy ranging from open-ended natural language reasoning to fully prescribed algorithmic execution, with intermediate levels providing partial pseudocode guidance. Our results show that intermediate autonomy levels consistently outperform both unguided agents and fully prescriptive specifications. These findings identify autonomy regulation as a key design principle for LLM-based distributed coordination.
CommentsA preliminary version of this work was published as an extended abstract in the Proceedings of AAMAS 2026
