arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.09244cs.AI
收藏

构建自主 LLM 智能体的基础

Fundamentals of Building Autonomous LLM Agents

Universitat Politècnica de Catalunya(巴塞罗那理工大学);Technische Universität München(慕尼黑技术大学)

Victor de Lamo Castrillo, Habtom Kahsay Gidey, Alexander Lenz, Alois Knoll

AI总结:

本文综述了自主LLM智能体的架构与实现,通过集成感知、推理、记忆和执行系统,旨在克服传统LLM局限,构建能自动化复杂任务并模仿人类认知过程的智能体。

摘要:

本文综述了由大型语言模型(LLMs)驱动的智能体的架构和实现方法。受传统 LLMs 在现实任务中的局限性所驱动,本研究旨在探索开发“代理型”LLMs 的模式,以自动化复杂任务并弥合与人类能力的性能差距。关键组件包括:将环境感知转换为有意义表示的感知系统;通过 Chain-of-Thought 和 Tree-of-Thought 等不同技术制定计划、适应反馈并评估行动的推理系统;通过短期和长期机制保留知识的记忆系统;以及将内部决策转化为具体行动的执行系统。本文展示了集成这些系统如何产生更强大、更通用的软件机器人,这些机器人模仿人类认知过程以实现自主和智能行为。

英文摘要:

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.

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。

↑