Authors: Xu Huang, Weiwen Liu, Xiaolong Chen, Xingmei Wang, Hao Wang, Defu Lian, Yasheng Wang, Ruiming Tang, Enhong Chen

Published on: February 05, 2024

Impact Score: 8.3

Arxiv code: Arxiv:2402.02716

Summary

• What is new: This paper is the first to systematically review and categorize the various approaches to leveraging Large Language Models (LLMs) for planning tasks in autonomous agents.
• Why this is important: The challenge of improving the planning abilities of autonomous agents using LLMs.
• What the research proposes: A taxonomy of existing works is introduced, grouping them into Task Decomposition, Plan Selection, External Module, Reflection, and Memory to guide further research efforts.
• Results: The paper provides a comprehensive analysis of current strategies and identifies key challenges for advancing the field of LLM-based agent planning.

Technical Details

Technological frameworks used: Not specifically mentioned

Models used: Large Language Models (LLMs)

Data used: Survey of existing literature on LLMs in autonomous agent planning

Potential Impact

Companies in the automation, AI development, and autonomous systems sectors could be disrupted or benefit from these insights.

Want to implement this idea in a business?

We have generated a startup concept here: IntelliPlanAI.