Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.18822 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915173535580160 |
|---|---|
| author | Su, Huangyuan Walsman, Aaron Garces, Daniel Kakade, Sham Gil, Stephanie |
| author_facet | Su, Huangyuan Walsman, Aaron Garces, Daniel Kakade, Sham Gil, Stephanie |
| contents | In this project, our goal is to determine how to leverage the world-knowledge of pretrained large language models for efficient and robust learning in multiagent decision making. We examine this in a taxi routing and assignment problem where agents must decide how to best pick up passengers in order to minimize overall waiting time. While this problem is situated on a graphical road network, we show that with the proper prompting zero-shot performance is quite strong on this task. Furthermore, with limited fine-tuning along with the one-at-a-time rollout algorithm for look ahead, LLMs can out-compete existing approaches with 50 times fewer environmental interactions. We also explore the benefits of various linguistic prompting approaches and show that including certain easy-to-compute information in the prompt significantly improves performance. Finally, we highlight the LLM's built-in semantic understanding, showing its ability to adapt to environmental factors through simple prompts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_18822 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Data-Efficient Multi-Agent Spatial Planning with LLMs Su, Huangyuan Walsman, Aaron Garces, Daniel Kakade, Sham Gil, Stephanie Artificial Intelligence Multiagent Systems In this project, our goal is to determine how to leverage the world-knowledge of pretrained large language models for efficient and robust learning in multiagent decision making. We examine this in a taxi routing and assignment problem where agents must decide how to best pick up passengers in order to minimize overall waiting time. While this problem is situated on a graphical road network, we show that with the proper prompting zero-shot performance is quite strong on this task. Furthermore, with limited fine-tuning along with the one-at-a-time rollout algorithm for look ahead, LLMs can out-compete existing approaches with 50 times fewer environmental interactions. We also explore the benefits of various linguistic prompting approaches and show that including certain easy-to-compute information in the prompt significantly improves performance. Finally, we highlight the LLM's built-in semantic understanding, showing its ability to adapt to environmental factors through simple prompts. |
| title | Data-Efficient Multi-Agent Spatial Planning with LLMs |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2502.18822 |