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

TL;DR

SayCanPay combines large language models with heuristic search and learnable domain knowledge to generate feasible, cost-effective plans, outperforming existing LLM planning methods.

Contribution

It introduces a novel framework that integrates LLMs with heuristic planning and learnable domain knowledge for improved plan generation.

Findings

Outperforms other LLM planning approaches in evaluations

Effectively integrates grounding and cost considerations into plans

Demonstrates the benefit of combining LLMs with heuristic search

Abstract

Large Language Models (LLMs) have demonstrated impressive planning abilities due to their vast "world knowledge". Yet, obtaining plans that are both feasible (grounded in affordances) and cost-effective (in plan length), remains a challenge, despite recent progress. This contrasts with heuristic planning methods that employ domain knowledge (formalized in action models such as PDDL) and heuristic search to generate feasible, optimal plans. Inspired by this, we propose to combine the power of LLMs and heuristic planning by leveraging the world knowledge of LLMs and the principles of heuristic search. Our approach, SayCanPay, employs LLMs to generate actions (Say) guided by learnable domain knowledge, that evaluates actions' feasibility (Can) and long-term reward/payoff (Pay), and heuristic search to select the best sequence of actions. Our contributions are (1) a novel framing of the LLM planning problem in the context of heuristic planning, (2) integrating grounding and cost-effective elements into the generated plans, and (3) using heuristic search over actions. Our extensive evaluations show that our model surpasses other LLM planning approaches.