[TOC]

  1. Title: LLM+P Empowering Large Language Models With Optimal Planning Proficiency
  2. Author: Bo Liu
  3. Publish Year: 5 May 2023
  4. Review Date: Mon, May 22, 2023
  5. url: https://arxiv.org/pdf/2304.11477.pdf

Summary of paper

Motivation

  • However, so far, LLMs cannot reliably solve long-horizon planning problems. By contrast, classical planners, once a problem is given in a formatted way, can use efficient search algorithms to quickly identify correct, or even optimal plans.

Contribution

  • introduce LLM+P, it takes in a natural language description of a planning problem, then return a correct plan for solving that problem in natural language. LLM+P does so by first converting the language description into a file written in the planning domain definition language (PDDL)
  • limitation of the paper: In this paper, we do not ask the LLM to recognize that it has been posed a prompt that is suitable for processing using the proposed LLM+P pipeline.

Some key terms

limitation of LLMs

  • LLMs have become amazingly proficient at linguistic competence — knowing how to say things; but they are not nearly as good at functional competence — knowing what to say.
  • image-20230522120405298

Architecture

  • image-20230522120543712

  • image-20230522120733413

  • assumptions

    • A chatbot knows when to trigger LLM+P based on its conversation with a human user
    • A domain PDDL file is provided for the problem the user asks for
    • A simple problem description in natural language and its corresponding problem PDDL file are also provided beforehand. (used as context)

Results

  • image-20230522120959547

Potential future work

  • ALFRED contains the exploration process. how can ensure that all the required objects are found during exploration