LLM+P: Empowering Large Language Models with Optimal Planning Proficiency

by   Bo Liu, et al.

Large language models (LLMs) have demonstrated remarkable zero-shot generalization abilities: state-of-the-art chatbots can provide plausible answers to many common questions that arise in daily life. 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. In an effort to get the best of both worlds, this paper introduces LLM+P, the first framework that incorporates the strengths of classical planners into LLMs. LLM+P takes in a natural language description of a planning problem, then returns a correct (or optimal) 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), then leveraging classical planners to quickly find a solution, and then translating the found solution back into natural language. Along with LLM+P, we define a diverse set of different benchmark problems taken from common planning scenarios. Via a comprehensive set of experiments on these benchmark problems, we find that LLM+P is able to provide optimal solutions for most problems, while LLMs fail to provide even feasible plans for most problems.[The code and results are publicly available at https://github.com/Cranial-XIX/llm-pddl.git.]


page 4

page 12

page 13


AutoScrum: Automating Project Planning Using Large Language Models

Recent advancements in the field of large language models have made it p...

Can Language Models Solve Graph Problems in Natural Language?

Large language models (LLMs) are increasingly adopted for a variety of t...

SayCanPay: Heuristic Planning with Large Language Models using Learnable Domain Knowledge

Large Language Models (LLMs) have demonstrated impressive planning abili...

ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning

Motivated by the substantial achievements observed in Large Language Mod...

Hierarchical Planning in the IPC

Over the last year, the amount of research in hierarchical planning has ...

What does a platypus look like? Generating customized prompts for zero-shot image classification

Open vocabulary models are a promising new paradigm for image classifica...

Plansformer: Generating Symbolic Plans using Transformers

Large Language Models (LLMs) have been the subject of active research, s...

Please sign up or login with your details

Forgot password? Click here to reset