Large Language Models as Commonsense Knowledge for Large-Scale Task Planning

By Zirui Zhao, Wee Sun Lee, David Hsu. Neural Information Processing Systems, 2023

397 citations recorded by the source corpus.

Large-scale task planning is a major challenge. Recent work exploits large language models (LLMs) directly as a policy and shows surprisingly interesting results. This paper shows that LLMs provide a commonsense model of the world in addition to a policy that acts on it. The world model and the policy can be combined in a search algorithm, such as Monte Carlo Tree Search (MCTS), to scale up task planning. In our new LLM-MCTS algorithm, the LLM-induced world model provides a commonsense prior belief for MCTS to achieve effective reasoning; the LLM-induced policy acts as a heuristic to guide the search, vastly improving search efficiency. Experiments show that LLM-MCTS outperforms both MCTS alone and policies induced by LLMs (GPT2 and GPT3.5) by a wide margin, for complex, novel tasks. Further experiments and analyses on multiple tasks -- multiplication, multi-hop travel planning, object rearrangement -- suggest minimum description length (MDL) as a general guiding principle: if the description length of the world model is substantially smaller than that of the policy, using LLM as a world model for model-based planning is likely better than using LLM solely as a policy.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5d32c364088733c6e8dadc9cf0baa26e10506d61

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Defu Lian
2. Xingmei Wang
3. Xiaolong Chen
4. Enhong Chen
5. Xu Huang

In Computer Vision and Pattern Recognition

1. Defu Lian
2. Enhong Chen

Citations in the corpus

• Understanding the planning of LLM agents: A survey (2024, methodology): “While existing surveys have attempted to summarize techniques for LLMs [Zhao et al. , 2023a], LLMs for decision-making [Yang et al. , 2023a], reasoning [Sun et al. , 2023], tool learning [Qin et al. , 2023], and autonomous agents [Wang et al. , 2023a], they often lack a detailed analysis of…”
• Aligning Cyber Space With Physical World: A Comprehensive Survey on Embodied AI (2024, neutral): “The comparative summary of the embodied robots, simulators, datasets, and approaches provides a clear picture of the recent development in embodied AI, which greatly benefits the future research along this emerging and promising research direction.”
• A Survey on Vision--Language--Action Models for Embodied AI (2024, neutral): “LLM-MCTS [81] builds upon RAP but extends the problem setting to POMDPs.”