Large Language Model Agent: A Survey on Methodology, Applications and Challenges

2025-03-27

AI Summary

This work addresses the fragmentation and lack of systematic frameworks in large language model (LLM)-based agent research. We propose the first methodology-centered, three-dimensional taxonomy—spanning *architecture design*, *collaboration mechanisms*, and *evolutionary pathways*—to unify key technical areas including multi-agent systems, prompt engineering, tool utilization, reflection mechanisms, reinforcement learning, and evaluation frameworks. By elucidating the intrinsic links between agent design principles and emergent behaviors in complex environments, we construct a structured knowledge graph and an open-source literature repository (Awesome-Agent-Papers). Our contributions are: (1) the first methodology-centered taxonomy for LLM agents; (2) a comprehensive, stack-wide survey—from monolithic agents to collective coordination; and (3) a reproducible evaluation benchmark alongside a forward-looking research roadmap. This work establishes both theoretical foundations and practical guidance for the LLM agent community.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

The era of intelligent agents is upon us, driven by revolutionary advancements in large language models. Large Language Model (LLM) agents, with goal-driven behaviors and dynamic adaptation capabilities, potentially represent a critical pathway toward artificial general intelligence. This survey systematically deconstructs LLM agent systems through a methodology-centered taxonomy, linking architectural foundations, collaboration mechanisms, and evolutionary pathways. We unify fragmented research threads by revealing fundamental connections between agent design principles and their emergent behaviors in complex environments. Our work provides a unified architectural perspective, examining how agents are constructed, how they collaborate, and how they evolve over time, while also addressing evaluation methodologies, tool applications, practical challenges, and diverse application domains. By surveying the latest developments in this rapidly evolving field, we offer researchers a structured taxonomy for understanding LLM agents and identify promising directions for future research. The collection is available at https://github.com/luo-junyu/Awesome-Agent-Papers.

Problem

• Surveying methodologies and applications of LLM agents
• Analyzing challenges in LLM agent development and deployment
• Providing a taxonomy for understanding LLM agent systems

Innovation

• Systematic deconstruction of LLM agent systems
• Unified architectural perspective on agent evolution
• Structured taxonomy for understanding LLM agents