Understanding the planning of LLM agents: A survey
It provides a foundational overview for researchers working on LLM agents, but it is incremental as a survey paper.
This survey systematically reviews recent works on improving the planning ability of LLM-based autonomous agents, categorizing them into areas like Task Decomposition and Plan Selection, and discusses future challenges.
As Large Language Models (LLMs) have shown significant intelligence, the progress to leverage LLMs as planning modules of autonomous agents has attracted more attention. This survey provides the first systematic view of LLM-based agents planning, covering recent works aiming to improve planning ability. We provide a taxonomy of existing works on LLM-Agent planning, which can be categorized into Task Decomposition, Plan Selection, External Module, Reflection and Memory. Comprehensive analyses are conducted for each direction, and further challenges for the field of research are discussed.