PDDLEGO: Iterative Planning in Textual Environments

TL;DR

PDDLEGO introduces an iterative planning method for partially-observed textual environments, enabling more efficient and coherent planning by progressively acquiring information and refining plans, outperforming end-to-end approaches.

Contribution

It presents a novel iterative planning approach that constructs and refines environment representations in partially-observed settings, improving planning efficiency and coherence.

Findings

Plans are 43% more efficient than end-to-end methods on Coin Collector.

Achieves 98% success on Cooking World, outperforming end-to-end LLMs.

Effective in partially-observed, complex textual environments.

Abstract

Planning in textual environments have been shown to be a long-standing challenge even for current models. A recent, promising line of work uses LLMs to generate a formal representation of the environment that can be solved by a symbolic planner. However, existing methods rely on a fully-observed environment where all entity states are initially known, so a one-off representation can be constructed, leading to a complete plan. In contrast, we tackle partially-observed environments where there is initially no sufficient information to plan for the end-goal. We propose PDDLEGO that iteratively construct a planning representation that can lead to a partial plan for a given sub-goal. By accomplishing the sub-goal, more information is acquired to augment the representation, eventually achieving the end-goal. We show that plans produced by few-shot PDDLEGO are 43% more efficient than generating plans end-to-end on the Coin Collector simulation, with strong performance (98%) on the more complex Cooking World simulation where end-to-end LLMs fail to generate coherent plans (4%).