Inspire or Predict? Exploring New Paradigms in Assisting Classical Planners with Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912987080556544 |
|---|---|
| author | Yu, Wenkai Tang, Jianhang Zhang, Yang Feng, Yixiong Wu, Celimuge Jin, Kebing Zhuo, Hankz Hankui |
| author_facet | Yu, Wenkai Tang, Jianhang Zhang, Yang Feng, Yixiong Wu, Celimuge Jin, Kebing Zhuo, Hankz Hankui |
| contents | Addressing large-scale planning problems has become one of the central challenges in the planning community, deriving from the state-space explosion caused by growing objects and actions. Recently, researchers have explored the effectiveness of leveraging Large Language Models (LLMs) to generate helpful actions and states to prune the search space. However, prior works have largely overlooked integrating LLMs with domain-specific knowledge to ensure valid plans. In this paper, we propose a novel LLM-assisted planner integrated with problem decomposition, which first decomposes large planning problems into multiple simpler sub-tasks with dependency construction and conflict detection. Then we explore two novel paradigms to utilize LLMs, i.e., LLM4Inspire and LLM4Predict, to assist problem decomposition, where LLM4Inspire provides heuristic guidance according to general knowledge and LLM4Predict employs domain-specific knowledge to infer intermediate conditions. We empirically validate the effectiveness of our planner across multiple domains, demonstrating the ability of search space partition when solving large-scale planning problems. The experimental results show that LLMs effectively locate feasible solutions when pruning the search space, where infusing domain-specific knowledge into LLMs, i.e., LLM4Predict, holds particular promise compared with LLM4Inspire, which offers general knowledge within LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_11524 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Inspire or Predict? Exploring New Paradigms in Assisting Classical Planners with Large Language Models Yu, Wenkai Tang, Jianhang Zhang, Yang Feng, Yixiong Wu, Celimuge Jin, Kebing Zhuo, Hankz Hankui Artificial Intelligence Addressing large-scale planning problems has become one of the central challenges in the planning community, deriving from the state-space explosion caused by growing objects and actions. Recently, researchers have explored the effectiveness of leveraging Large Language Models (LLMs) to generate helpful actions and states to prune the search space. However, prior works have largely overlooked integrating LLMs with domain-specific knowledge to ensure valid plans. In this paper, we propose a novel LLM-assisted planner integrated with problem decomposition, which first decomposes large planning problems into multiple simpler sub-tasks with dependency construction and conflict detection. Then we explore two novel paradigms to utilize LLMs, i.e., LLM4Inspire and LLM4Predict, to assist problem decomposition, where LLM4Inspire provides heuristic guidance according to general knowledge and LLM4Predict employs domain-specific knowledge to infer intermediate conditions. We empirically validate the effectiveness of our planner across multiple domains, demonstrating the ability of search space partition when solving large-scale planning problems. The experimental results show that LLMs effectively locate feasible solutions when pruning the search space, where infusing domain-specific knowledge into LLMs, i.e., LLM4Predict, holds particular promise compared with LLM4Inspire, which offers general knowledge within LLMs. |
| title | Inspire or Predict? Exploring New Paradigms in Assisting Classical Planners with Large Language Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.11524 |