发现大模型生成存在微观平衡，揭示其背后潜在能量场机制。
Detailed balance in large language model-driven agents
- 基于最小作用量原理，测量大模型状态转移概率
- 实验证明生成过程满足细致平衡，无方向性偏好
- 为智能体宏观动力学提供可预测的物理类理论框架
大型语言模型（LLM）驱动的智能体正成为解决复杂问题的新范式。尽管实践上取得成功，但缺乏统一的宏观动态理论框架。本文提出一种基于最小作用量原理的方法，用于估计嵌入在智能体中的LLM的生成方向性。通过实验测量LLM生成状态间的转移概率，我们统计发现生成转移满足细致平衡，表明大模型生成并非依赖显式规则集或策略学习，而是隐式学习一类跨架构与提示模板的底层势能函数。据我们所知，这是首个不依赖具体模型细节的、关于大模型生成动力学的宏观物理规律发现。本工作旨在建立复杂人工智能系统的宏观动力学理论，推动智能体研究从工程实践迈向可测量、可预测的科学体系。
原文摘要 · Abstract (English)
Large language model (LLM)-driven agents are emerging as a powerful new paradigm for solving complex problems. Despite the empirical success of these practices, a theoretical framework to understand and unify their macroscopic dynamics remains lacking. This Letter proposes a method based on the least action principle to estimate the underlying generative directionality of LLMs embedded within agents. By experimentally measuring the transition probabilities between LLM-generated states, we statistically discover a detailed balance in LLM-generated transitions, indicating that LLM generation may not be achieved by generally learning rule sets and strategies, but rather by implicitly learning a class of underlying potential functions that may transcend different LLM architectures and prompt templates. To our knowledge, this is the first discovery of a macroscopic physical law in LLM generative dynamics that does not depend on specific model details. This work is an attempt to establish a macroscopic dynamics theory of complex AI systems, aiming to elevate the study of AI agents from a collection of engineering practices to a science built on effective measurements that are predictable and quantifiable.
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。