TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Models

TL;DR

This paper introduces TwoStep, a hybrid approach combining classical planners and large language models to improve multi-agent task planning efficiency and success, approximating human-like goal decomposition.

Contribution

It presents a novel method that leverages LLMs for goal decomposition in multi-agent planning, enhancing speed and success rates over traditional PDDL-based methods.

Findings

LLM-based goal decomposition reduces planning time.

Achieves fewer execution steps than single-agent plans.

Guarantees execution success in multi-agent scenarios.

Abstract

Classical planning formulations like the Planning Domain Definition Language (PDDL) admit action sequences guaranteed to achieve a goal state given an initial state if any are possible. However, reasoning problems defined in PDDL do not capture temporal aspects of action taking, such as concurrent actions between two agents when there are no conflicting conditions, without significant modification and definition to existing PDDL domains. A human expert aware of such constraints can decompose a goal into subgoals, each reachable through single agent planning, to take advantage of simultaneous actions. In contrast to classical planning, large language models (LLMs) directly used for inferring plan steps rarely guarantee execution success, but are capable of leveraging commonsense reasoning to assemble action sequences. We combine the strengths of both classical planning and LLMs by approximating human intuitions for multi-agent planning goal decomposition. We demonstrate that LLM-based goal decomposition leads to faster planning times than solving multi-agent PDDL problems directly while simultaneously achieving fewer plan execution steps than a single agent plan alone, as well as most multiagent plans, while guaranteeing execution success. Additionally, we find that LLM-based approximations of subgoals result in similar multi-agent execution lengths to those specified by human experts. Website and resources at https://glamor-usc.github.io/twostep