From Dialogue to Execution: Mixture-of-Agents Assisted Interactive Planning for Behavior Tree-Based Long-Horizon Robot Execution

[2603.01113] From Dialogue to Execution: Mixture-of-Agents Assisted Interactive Planning for Behavior Tree-Based Long-Horizon Robot Execution Skip to main content Search Submit Donate Log in Computer Science > Robotics arXiv:2603.01113 (cs) [Submitted on 1 Mar 2026 ( v1 ), last revised 28 Aug 2026 (this version, v3)] Title: From Dialogue to Execution: Mixture-of-Agents Assisted Interactive Planning for Behavior Tree-Based Long-Horizon Robot Execution Authors: Kanata Suzuki , Kazuki Hori , Haruka Miyoshi , Shuhei Kurita , Tetsuya Ogata View PDF HTML (experimental) Abstract: Interactive task planning with large language models (LLMs) lets robots generate high-level action plans from natural language, but over long horizons it asks many questions, and tabular plan representations become hard to manage. We propose a framework that integrates Mixture-of-Agents (MoA)-based proxy answering into interactive planning and generates Behavior Trees (BTs) for structured long-term execution. We formulate the MoA as an abstention-based delegation cascade: each expert agent answers only the questions entailed by its own prerequisite description, forwards the rest unchanged, and the human user acts as the terminal fallback. The question set is thus partitioned disjointly, so no answer fusion or arbitration is required while every question is still resolved. The BT represents task logic hierarchically and enables retry and dynamic switching among robot policies. Experiments on a cocktail-making task show that the method removes approximately 27% of the human responses while keeping the generated BTs within the baseline generator's own variance. Real-robot experiments on a smoothie-making task further demonstrate successful long-horizon execution with adaptive policy switching and recovery from action failures. We further analyze the failure modes of the framework and show that its applicability boundary is set by the reliability of the weakest action node rather than by the planner. These results indicate that MoA-assisted interactive planning improves dialogue efficiency while preserving execution quality in real-world robotic tasks. Subjects: Robotics (cs.RO) Cite as: arXiv:2603.01113 [cs.RO] (or arXiv:2603.01113v3 [cs.RO] for this version) https://doi.org/10.48550/arXiv.2603.01113 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Kanata Suzuki [ view email ] [v1] Sun, 1 Mar 2026 13:54:51 UTC (1,134 KB) [v2] Mon, 24 Aug 2026 21:50:07 UTC (908 KB) [v3] Fri, 28 Aug 2026 02:33:50 UTC (908 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Current browse context: cs.RO < prev | next > new | recent | 2026-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• From Dialogue to Execution: Mixture-of-Agents Assisted Interactive Planning for Behavior Tree-Based Long-Horizon Robot Execution#682598
• Adaptation Needs in Robotic Systems: Assessing Behavior Trees and Their Enhancement#660877
• TANDEM: Task and Motion Planning with As-Needed Demonstrations for Efficient Vision-Language-Action Model Fine-tuning#1064858
• Plan Along the Way: Event-Triggered Foundation-Model Planning for TAMP Execution in Partially Observable Manipulation#784838
• Plan Along the Way: Event-Triggered Foundation-Model Planning for TAMP Execution in Partially Observable Manipulation#783248