多智能体系统通过约束分解实现隐藏的稳定解结构。
Multi-Agent Constraint Factorization Reveals Latent Invariant Solution Structure
- 将每个智能体视为施加不同约束，形成约束分解的组合机制。
- 在温和条件下，系统收敛到各约束集交集的不变解集。
- 适用于理解大模型对话系统的协作原理，适合研究多智能体协同者。
由大型语言模型组成的多智能体系统（MAS）尽管共享相同信息，仍表现出更优的问题求解性能。本文基于算子理论与约束优化，提出正式解释：每个智能体对共享解状态施加不同的有效性约束，整体系统实现约束执行算子的因子化组合。在温和条件下，该动态收敛至由各智能体约束集交集定义的不变解集。此类不变结构通常无法被单一智能体同时施加所有约束时动态达到，即使其表达能力与信息相同。我们还将该结果从精确约束推广至软约束，借助邻近算子，并将其形式化应用于当前主流文本对话系统。
原文摘要 · Abstract (English)
Multi-agent systems (MAS) composed of large language models often exhibit improved problem-solving performance despite operating on identical information. In this work, we provide a formal explanation for this phenomenon grounded in operator theory and constrained optimization. We model each agent as enforcing a distinct family of validity constraints on a shared solution state, and show that a MAS implements a factorized composition of constraint-enforcement operators. Under mild conditions, these dynamics converge to invariant solution sets defined by the intersection of agent constraint sets. Such invariant structures are generally not dynamically accessible to a single agent applying all constraints simultaneously, even when expressive capacity and information are identical. We extend this result from exact constraint enforcement to soft constraints via proximal operators, and apply the formalism to contemporary text-based dialog systems.
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。