🤖 AI Summary
Existing LLM-based agent tool integration suffers from architectural fragmentation, insufficient modularity, and terminological inconsistency. Method: This paper proposes the first unified modeling framework for LLM-based agents. Its core innovations include: (1) formally defining the “core agent” as a structured composition of five cohesive modules—planning, memory, persona, execution, and safety—and introducing an active/passive typology to enable multi-core coordination; (2) proposing a novel layered architecture with explicit safety modeling; and (3) establishing a composable, extensible hybrid agent design paradigm. Contribution/Results: Leveraging this framework, we systematically map and clarify the architectural essence of 13 state-of-the-art agents; validate five novel active/passive hybrid architectures; and identify critical cross-agent integration challenges alongside concrete optimization pathways. The framework advances principled, scalable, and secure agent design.
📝 Abstract
In an era where vast amounts of data are collected and processed from diverse sources, there is a growing demand to develop sophisticated AI systems capable of intelligently fusing and analyzing this information. To address these challenges, researchers have turned towards integrating tools into LLM-powered agents to enhance the overall information fusion process. However, the conjunction of these technologies and the proposed enhancements in several state-of-the-art works followed a non-unified software architecture resulting in a lack of modularity and terminological inconsistencies among researchers. To address these issues, we propose a novel LLM-based Agent Unified Modeling Framework (LLM-Agent-UMF) that aims to establish a clear foundation for agent development from both functional and software architectural perspectives. Our framework distinguishes between the different components of an LLM-based agent, setting LLMs, and tools apart from a new element, the core-agent, playing the role of the central coordinator of the agent. This pivotal entity comprises five modules: planning, memory, profile, action, and security - the latter often neglected in previous works. By classifying core-agents into passive and active types based on their authoritative natures, we propose various multi-core agent architectures that combine unique characteristics of distinctive agents to tackle complex tasks more efficiently. We evaluate our framework by applying it to thirteen state-of-the-art agents, thereby demonstrating its alignment with their functionalities and clarifying the overlooked architectural aspects. Moreover, we thoroughly assess five of our proposed architectures through the integration of existing agents into new hybrid active/passive core-agents architectures. This analysis provides insights into potential improvements and highlights challenges involved in combining specific agents.