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

TL;DR

This paper introduces a formal model for analyzing LLM-based agents through structural context and semantic dynamics, enabling systematic design and comparison, and demonstrating significant performance improvements in complex tasks.

Contribution

It proposes the Structural Context Model and a semantic dynamics analysis workflow, providing a formal foundation and practical tools for LLM agent design and evaluation.

Findings

Achieved up to 32 percentage points improvement in success rate.

Demonstrated effectiveness on dynamic monkey-banana problem variants.

Provided a formal framework for implementation-independent analysis.

Abstract

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.