A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning
This survey addresses the problem of inconsistent taxonomy and complex workflows in LLM-based agent research, providing a structured review for researchers and practitioners in AI.
The authors tackled the challenge of understanding and comparing diverse frameworks for LLM-based agents by introducing a unified taxonomy to review tool use, planning, and feedback learning paradigms, resulting in a systematic analysis that identifies limitations and future work.
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.