Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.01917 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913973430910976 |
|---|---|
| author | Agarwal, Krish Jiang, Yuqian Hu, Jiaheng Liu, Bo Stone, Peter |
| author_facet | Agarwal, Krish Jiang, Yuqian Hu, Jiaheng Liu, Bo Stone, Peter |
| contents | By combining classical planning methods with large language models (LLMs), recent research such as LLM+P has enabled agents to plan for general tasks given in natural language. However, scaling these methods to general-purpose service robots remains challenging: (1) classical planning algorithms generally require a detailed and consistent specification of the environment, which is not always readily available; and (2) existing frameworks mainly focus on isolated planning tasks, whereas robots are often meant to serve in long-term continuous deployments, and therefore must maintain a dynamic memory of the environment which can be updated with multi-modal inputs and extracted as planning knowledge for future tasks. To address these two issues, this paper introduces L3M+P (Lifelong LLM+P), a framework that uses an external knowledge graph as a representation of the world state. The graph can be updated from multiple sources of information, including sensory input and natural language interactions with humans. L3M+P enforces rules for the expected format of the absolute world state graph to maintain consistency between graph updates. At planning time, given a natural language description of a task, L3M+P retrieves context from the knowledge graph and generates a problem definition for classical planners. Evaluated on household robot simulators and on a real-world service robot, L3M+P achieves significant improvement over baseline methods both on accurately registering natural language state changes and on correctly generating plans, thanks to the knowledge graph retrieval and verification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01917 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | L3M+P: Lifelong Planning with Large Language Models Agarwal, Krish Jiang, Yuqian Hu, Jiaheng Liu, Bo Stone, Peter Robotics Artificial Intelligence By combining classical planning methods with large language models (LLMs), recent research such as LLM+P has enabled agents to plan for general tasks given in natural language. However, scaling these methods to general-purpose service robots remains challenging: (1) classical planning algorithms generally require a detailed and consistent specification of the environment, which is not always readily available; and (2) existing frameworks mainly focus on isolated planning tasks, whereas robots are often meant to serve in long-term continuous deployments, and therefore must maintain a dynamic memory of the environment which can be updated with multi-modal inputs and extracted as planning knowledge for future tasks. To address these two issues, this paper introduces L3M+P (Lifelong LLM+P), a framework that uses an external knowledge graph as a representation of the world state. The graph can be updated from multiple sources of information, including sensory input and natural language interactions with humans. L3M+P enforces rules for the expected format of the absolute world state graph to maintain consistency between graph updates. At planning time, given a natural language description of a task, L3M+P retrieves context from the knowledge graph and generates a problem definition for classical planners. Evaluated on household robot simulators and on a real-world service robot, L3M+P achieves significant improvement over baseline methods both on accurately registering natural language state changes and on correctly generating plans, thanks to the knowledge graph retrieval and verification. |
| title | L3M+P: Lifelong Planning with Large Language Models |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2508.01917 |