基于LLM的智能体的主要范式综述：工具使用（含RAG）、规划与反馈学习
A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning
AI总结：
针对LLM智能体的工具使用、规划和反馈学习三大范式框架存在分类不一致、流程复杂的问题，本综述提出统一分类法系统梳理这些框架，定义环境/任务、LMPRs角色及通用工作流程，支持跨范式比较并指出局限与未来方向。
摘要：
工具使用、规划和反馈学习是当前在各类任务中开发基于大语言模型（LLM）的智能体的三大主要范式。尽管针对每个范式已设计出众多框架，但它们复杂的工作流程和不一致的分类法为跨范式理解和综述这些框架带来挑战。本综述引入统一分类法来系统综述和讨论这些框架：1）该分类法定义了环境/任务、常见的LLM特征角色（LMPRs，包括策略模型、评估器和动态模型）以及先前工作中发现的通用工作流程；2）它支持对不同智能体范式和框架中LMPRs实现及工作流程设计的关键视角进行比较；3）最后，我们指出现有工作流程设计的三大局限并系统讨论未来方向。相关资源已公开于GitHub仓库https://github.com/xinzhel/LLM-Agent-Survey。
英文摘要：
Tool use, planning, and feedback learning are currently three prominent paradigms for developing Large Language Model (LLM)-based agents across various tasks. Although numerous frameworks have been devised for each paradigm, their intricate workflows and inconsistent taxonomy create challenges in understanding and reviewing the frameworks across different paradigms. This survey introduces a unified taxonomy to systematically review and discuss these frameworks. Specifically, 1) the taxonomy defines environments/tasks, common LLM-profiled roles or LMPRs (policy models, evaluators, and dynamic models), and universally applicable workflows found in prior work, and 2) it enables a comparison of key perspectives on the implementations of LMPRs and workflow designs across different agent paradigms and frameworks. 3) Finally, we identify three limitations in existing workflow designs and systematically discuss the future work. Resources have been made publicly available at in our GitHub repository https://github.com/xinzhel/LLM-Agent-Survey.
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。
