English

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

Robotics 2026-03-03 v1

Abstract

Interactive task planning with large language models (LLMs) enables robots to generate high-level action plans from natural language instructions. However, in long-horizon tasks, such approaches often require many questions, increasing user burden. Moreover, flat plan representations become difficult to manage as task complexity grows. 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. The MoA consists of multiple LLM-based expert agents that answer general or domain-specific questions when possible, reducing unnecessary human intervention. The resulting BT hierarchically represents task logic and enables retry mechanisms and dynamic switching among multiple robot policies. Experiments on cocktail-making tasks show that the proposed method reduces human response requirements by approximately 27% while maintaining structural and semantic similarity to fully human-answered BTs. Real-robot experiments on a smoothie-making task further demonstrate successful long-horizon execution with adaptive policy switching and recovery from action failures. These results indicate that MoA-assisted interactive planning improves dialogue efficiency while preserving execution quality in real-world robotic tasks.

Keywords

Cite

@article{arxiv.2603.01113,
  title  = {From Dialogue to Execution: Mixture-of-Agents Assisted Interactive Planning for Behavior Tree-Based Long-Horizon Robot Execution},
  author = {Kanata Suzuki and Kazuki Hori and Haruka Miyoshi and Shuhei Kurita and Tetsuya Ogata},
  journal= {arXiv preprint arXiv:2603.01113},
  year   = {2026}
}
R2 v1 2026-07-01T10:57:59.221Z