大语言模型驱动代理中的详尽平衡
Detailed balance in large language model-driven agents
AI总结:
本文提出基于最小作用原理的方法,发现LLM生成中存在详尽平衡,揭示LLM生成可能通过隐式学习潜在函数而非显式规则集。
摘要:
大型语言模型(LLM)驱动的代理正成为解决复杂问题的强大新范式。尽管这些实践在经验上取得了成功,但缺乏一个理论框架来理解和统一其宏观动力学。本信件提出了一种基于最小作用原理的方法,用于估计嵌入在代理中的LLM所具有的生成方向性。通过实验测量LLM生成状态之间的转移概率,我们统计上发现LLM生成转换中存在详尽平衡,表明LLM生成可能不是通过一般学习规则集和策略实现的,而是通过隐式学习一类潜在的潜在函数,这些函数可能超越不同的LLM架构和提示模板。据我们所知,这是首次在LLM生成动力学中发现一个不依赖特定模型细节的宏观物理定律。本工作旨在建立复杂人工智能系统的宏观动力学理论,旨在将AI代理的研究从工程实践的集合提升到建立在可预测和量化的有效测量之上的科学。
英文摘要:
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 paper 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 report evidence consistent with a tendency toward 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 provides an effective macroscopic description of 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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。