{"ID":2884196,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.07421","arxiv_id":"2508.07421","title":"Triple-S: A Collaborative Multi-LLM Framework for Solving Long-Horizon Implicative Tasks in Robotics","abstract":"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.","short_abstract":"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 Tri...","url_abs":"https://arxiv.org/abs/2508.07421","url_pdf":"https://arxiv.org/pdf/2508.07421v1","authors":"[\"Zixi Jia\",\"Hongbin Gao\",\"Fashe Li\",\"Jiqiang Liu\",\"Hexiao Li\",\"Qinghua Liu\"]","published":"2025-08-10T16:33:32Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":611064,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2884196,"paper_url":"https://arxiv.org/abs/2508.07421","paper_title":"Triple-S: A Collaborative Multi-LLM Framework for Solving Long-Horizon Implicative Tasks in Robotics","repo_url":"https://github.com/Ghbbbbb/Triple-S","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}