让大模型像人一样思考并执行复杂任务，构建自主智能体。
Fundamentals of Building Autonomous LLM Agents
- 分感知、推理、记忆、执行四模块，模仿人类认知流程
- 结合思维链与思维树，提升规划与自适应能力
- 适合研究智能体架构或想落地自动化系统的人
本文综述了基于大语言模型（LLMs）的智能体架构与实现方法。针对传统LLMs在真实任务中的局限性，研究旨在探索构建‘自主型’LLM的模式，以自动化复杂任务并缩小与人类能力的差距。核心组件包括：将环境感知转化为有意义表征的感知系统；通过思维链（Chain-of-Thought）和思维树（Tree-of-Thought）等技术进行计划制定、反馈适应与行动评估的推理系统；结合短期与长期机制的记忆系统；以及将内部决策转化为具体动作的执行系统。研究表明，整合这些模块可使软件机器人具备更强的泛化能力与自主智能行为，更贴近人类认知过程。
原文摘要 · Abstract (English)
This paper reviews the architecture and implementation methods of agents powered by large language models (LLMs). Motivated by the limitations of traditional LLMs in real-world tasks, the research aims to explore patterns to develop "agentic" LLMs that can automate complex tasks and bridge the performance gap with human capabilities. Key components include a perception system that converts environmental percepts into meaningful representations; a reasoning system that formulates plans, adapts to feedback, and evaluates actions through different techniques like Chain-of-Thought and Tree-of-Thought; a memory system that retains knowledge through both short-term and long-term mechanisms; and an execution system that translates internal decisions into concrete actions. This paper shows how integrating these systems leads to more capable and generalized software bots that mimic human cognitive processes for autonomous and intelligent behavior.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。