arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.08276cs.AI
收藏

通过结构上下文建模和语义动态分析正式化基于大语言模型的智能体设计

Toward Formalizing LLM-Based Agent Designs through Structural Context Modeling and Semantic Dynamics Analysis

Haoyu Jia, Kento Kawaharazuka, Kei Okada

AI总结:

本文提出结构上下文模型和语义动态分析工作流,旨在通过形式化方法提升大语言模型智能体设计的可分析性和一致性。

摘要:

当前关于大语言模型(LLM)智能体的研究碎片化:概念框架和方法论原则的讨论经常与低层次实现细节交织在一起,导致读者和作者在众多表面上不同的概念中迷失方向。我们主张这种碎片化主要源于缺乏一个可分析、自洽的正式模型,该模型能够实现无关的实现方式下对LLM智能体的表征和比较。为了解决这一缺口,我们提出了结构上下文模型,一个用于分析和比较LLM智能体的正式模型,从上下文结构的角度出发。在此基础上,我们引入了两个互补的组件,共同覆盖LLM智能体研究和开发的整个生命周期:(1)一个声明性实现框架;和(2)一个可持续的智能体工程工作流,语义动态分析。所提出的工作流为智能体机制提供了原则性的见解,并支持快速、系统的迭代设计。我们通过动态变体的猴子-香蕉问题展示了完整框架的有效性,其中使用我们方法设计的智能体在最具有挑战性的设置中成功率达到32个百分点的提升。

英文摘要:

Current research on large language model (LLM) agents is fragmented: discussions of conceptual frameworks and methodological principles are frequently intertwined with low-level implementation details, causing both readers and authors to lose track amid a proliferation of superficially distinct concepts. We argue that this fragmentation largely stems from the absence of an analyzable, self-consistent formal model that enables implementation-independent characterization and comparison of LLM agents. To address this gap, we propose the \texttt{Structural Context Model}, a formal model for analyzing and comparing LLM agents from the perspective of context structure. Building upon this foundation, we introduce two complementary components that together span the full lifecycle of LLM agent research and development: (1) a declarative implementation framework; and (2) a sustainable agent engineering workflow, \texttt{Semantic Dynamics Analysis}. The proposed workflow provides principled insights into agent mechanisms and supports rapid, systematic design iteration. We demonstrate the effectiveness of the complete framework on dynamic variants of the monkey-banana problem, where agents engineered using our approach achieve up to a 32 percentage points improvement in success rate on the most challenging setting.

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。

↑