Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning

By Lin Guan, Karthik Valmeekam, Sarath Sreedharan, Subbarao Kambhampati. Neural Information Processing Systems, 2023

316 citations recorded by the source corpus.

There is a growing interest in applying pre-trained large language models (LLMs) to planning problems. However, methods that use LLMs directly as planners are currently impractical due to several factors, including limited correctness of plans, strong reliance on feedback from interactions with simulators or even the actual environment, and the inefficiency in utilizing human feedback. In this work, we introduce a novel alternative paradigm that constructs an explicit world (domain) model in planning domain definition language (PDDL) and then uses it to plan with sound domain-independent planners. To address the fact that LLMs may not generate a fully functional PDDL model initially, we employ LLMs as an interface between PDDL and sources of corrective feedback, such as PDDL validators and humans. For users who lack a background in PDDL, we show that LLMs can translate PDDL into natural language and effectively encode corrective feedback back to the underlying domain model. Our framework not only enjoys the correctness guarantee offered by the external planners but also reduces human involvement by allowing users to correct domain models at the beginning, rather than inspecting and correcting (through interactive prompting) every generated plan as in previous work. On two IPC domains and a Household domain that is more complicated than commonly used benchmarks such as ALFWorld, we demonstrate that GPT-4 can be leveraged to produce high-quality PDDL models for over 40 actions, and the corrected PDDL models are then used to successfully solve 48 challenging planning tasks. Resources, including the source code, are released at: https://guansuns.github.io/pages/llm-dm.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/4f601b4e561557c7a0bd5a741a54cabaec7dc70e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

A Survey on Vision--Language--Action Models for Embodied AI (2024, unknown): “LLM-DM [77] uses an LLM to construct world models in planning domain definition language (PDDL)—a capability that LLM+P [78] did not achieve, as its PDDL world model was hand-crafted.”
Cognitive Architectures for Language Agents (2023, background): “Solving these issues will significantly improve LLMs’ utilities as agent backbones.”
Understanding the planning of LLM agents: A survey (2024, methodology): “LLM+PDDL [Guan et al. , 2023] also utilizes the PDDL language to formalize the task, incorporating an additional step for manual verification to check for potential issues in the PDDL model generated by LLM.”
PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change (2022, background): “These roles range from generating plans [11, 33] and heuristics [33, 1] to extracting planning knowledge [7].”