LLMs as Planning Modelers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models

2025-03-22

AI Summary

Large language models (LLMs) excel at natural language understanding but lack robustness in long-horizon automated planning tasks requiring structured, symbolic reasoning. This paper pioneers the conceptualization of LLMs as “planning modelers,” systematically surveying their role in generating formal symbolic planning models—such as PDDL—from natural language specifications, thereby establishing a unified analytical framework bridging NLP and automated planning. Methodologically, we integrate prompt engineering, few-shot learning, programmatic validation, and neuro-symbolic interfaces, while incorporating formal verification and off-the-shelf planners. Through a taxonomy-driven evaluation of over 100 works, we identify five fundamental bottlenecks—including semantic gaps and insufficient action generalization—and propose scalable solutions such as a verifiable modeling pipeline. Our approach substantially enhances the interpretability, reliability, and automation capability of symbolic planners.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: (Large) Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Large Language Models (LLMs) excel in various natural language tasks but often struggle with long-horizon planning problems requiring structured reasoning. This limitation has drawn interest in integrating neuro-symbolic approaches within the Automated Planning (AP) and Natural Language Processing (NLP) communities. However, identifying optimal AP deployment frameworks can be daunting. This paper aims to provide a timely survey of the current research with an in-depth analysis, positioning LLMs as tools for extracting and refining planning models to support reliable AP planners. By systematically reviewing the current state of research, we highlight methodologies, and identify critical challenges and future directions, hoping to contribute to the joint research on NLP and Automated Planning.

Problem

• LLMs struggle with structured long-horizon planning tasks
• Integrating neuro-symbolic methods for Automated Planning challenges
• Surveying LLM-based planning model extraction and refinement

Innovation

• LLMs extract and refine planning models
• Neuro-symbolic approaches enhance structured reasoning
• Survey identifies optimal AP deployment frameworks