Planning in the Dark: LLM-Symbolic Planning Pipeline Without Experts
Open Access
- 11 April 2025
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (25) , 26542-26550
Abstract
Large Language Models (LLMs) have shown promise in solving natural language-described planning tasks, but their direct use often leads to inconsistent reasoning and hallucination. While hybrid LLM-symbolic planning pipelines have emerged as a more robust alternative, they typically require extensive expert intervention to refine and validate generated action schemas. It not only limits scalability but also introduces a potential for biased interpretation, as a single expert's interpretation of ambiguous natural language descriptions might not align with the user's actual intent. To address this, we propose a novel approach that constructs an action schema library to generate multiple candidates, accounting for the diverse possible interpretations of natural language descriptions. We further introduce a semantic validation and ranking module that automatically filter and rank these candidates without expert-in-the-loop. The experiments showed our pipeline maintains superiority in planning over the direct LLM planning approach. These findings demonstrate the feasibility of a fully automated end-to-end LLM-symbolic planner that requires no expert intervention, opening up the possibility for a broader audience to engage with AI planning with less prerequisite of domain expertise.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)Proceedings of the International Conference on Automated Planning and Scheduling, 2024
- Large Language Models are Zero-Shot Rankers for Recommender Systems2024
- Thought of Search: Planning with Language Models Through The Lens of Efficiency2024
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models2023
- On the Planning Abilities of Large Language Models - A Critical Investigation2023
- Large Language Models Are Zero-Shot Reasoners2022
- Least Ambiguous Set-Valued Classifiers With Bounded Error LevelsJournal of the American Statistical Association, 2018
- The Fifth International Competition on Knowledge Engineering for Planning and Scheduling: Summary and TrendsAI Magazine, 2017
- Concise finite-domain representations for PDDL planning tasksArtificial Intelligence, 2009
- Planning as heuristic searchArtificial Intelligence, 2001