Triple-S: A Collaborative Multi-LLM Framework for Solving Long-Horizon Implicative Tasks in Robotics
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_ | 1866913983090393088 |
|---|---|
| author | Jia, Zixi Gao, Hongbin Li, Fashe Liu, Jiqiang Li, Hexiao Liu, Qinghua |
| author_facet | Jia, Zixi Gao, Hongbin Li, Fashe Liu, Jiqiang Li, Hexiao Liu, Qinghua |
| contents | Leveraging Large Language Models (LLMs) to write policy code for controlling robots has gained significant attention. However, in long-horizon implicative tasks, this approach often results in API parameter, comments and sequencing errors, leading to task failure. To address this problem, we propose a collaborative Triple-S framework that involves multiple LLMs. Through In-Context Learning, different LLMs assume specific roles in a closed-loop Simplification-Solution-Summary process, effectively improving success rates and robustness in long-horizon implicative tasks. Additionally, a novel demonstration library update mechanism which learned from success allows it to generalize to previously failed tasks. We validate the framework in the Long-horizon Desktop Implicative Placement (LDIP) dataset across various baseline models, where Triple-S successfully executes 89% of tasks in both observable and partially observable scenarios. Experiments in both simulation and real-world robot settings further validated the effectiveness of Triple-S. Our code and dataset is available at: https://github.com/Ghbbbbb/Triple-S. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07421 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Triple-S: A Collaborative Multi-LLM Framework for Solving Long-Horizon Implicative Tasks in Robotics Jia, Zixi Gao, Hongbin Li, Fashe Liu, Jiqiang Li, Hexiao Liu, Qinghua Robotics Leveraging Large Language Models (LLMs) to write policy code for controlling robots has gained significant attention. However, in long-horizon implicative tasks, this approach often results in API parameter, comments and sequencing errors, leading to task failure. To address this problem, we propose a collaborative Triple-S framework that involves multiple LLMs. Through In-Context Learning, different LLMs assume specific roles in a closed-loop Simplification-Solution-Summary process, effectively improving success rates and robustness in long-horizon implicative tasks. Additionally, a novel demonstration library update mechanism which learned from success allows it to generalize to previously failed tasks. We validate the framework in the Long-horizon Desktop Implicative Placement (LDIP) dataset across various baseline models, where Triple-S successfully executes 89% of tasks in both observable and partially observable scenarios. Experiments in both simulation and real-world robot settings further validated the effectiveness of Triple-S. Our code and dataset is available at: https://github.com/Ghbbbbb/Triple-S. |
| title | Triple-S: A Collaborative Multi-LLM Framework for Solving Long-Horizon Implicative Tasks in Robotics |
| topic | Robotics |
| url | https://arxiv.org/abs/2508.07421 |