Abstract
Hierarchical planning frameworks combine skills from multiple robot control policies for long-horizon task execution, where determining when to terminate the current skill and advance to the next subtask is essential. Existing approaches often rely on pre-designed completion signal checkers that are hard to obtain in real-world execution. Large-scale vision-language models (VLMs) offer strong reasoning capabilities, but their decision boundaries are not inherently aligned with task completion criteria, while cloud deployment and lengthy reasoning introduce substantial latency, limiting real-time monitoring. We propose StageGuard, an agentic distillation framework for accurate and efficient stage-transition decisions. StageGuard combines teacher-model reasoning with demonstration trajectories to generate structured explanations of subtask completion and policy switching. A lightweight student VLM uses these explanations to generate compact self-explanations, which are used for supervised fine-tuning. We evaluate stage-transition prediction on trajectories from two benchmarks and assess closed-loop task success through integration into hierarchical robot control on BEHAVIOR-1K, with further validation on real robots. Results show substantial improvements in stage-transition prediction while supporting efficient online monitoring.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Huang, J., Hu, Y., Li, Z., Qi, R., Xiao, Y., Wu, Y., Ba, T., Zhang, Z., & Zhang, Y. (2026). StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation. https://omanscience.com/en/articles/stageguard-learning-stage-transitions-for-long-horizon-robot-tasks-via-agentic-distillation
MLA 9
Huang, Jinbang, et al. "StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation." https://omanscience.com/en/articles/stageguard-learning-stage-transitions-for-long-horizon-robot-tasks-via-agentic-distillation.
Chicago (author–date)
Huang, Jinbang, Yuanzhao Hu, Zhiyuan Li, Ran Qi, Yixin Xiao, Yangzheng Wu, Tengyue Ba, Zhanguang Zhang, and Yingxue Zhang. 2026. "StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation." https://omanscience.com/en/articles/stageguard-learning-stage-transitions-for-long-horizon-robot-tasks-via-agentic-distillation.
Harvard
Huang, J., Hu, Y., Li, Z., Qi, R., Xiao, Y., Wu, Y., Ba, T., Zhang, Z. and Zhang, Y. (2026) 'StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation', Available at: https://omanscience.com/en/articles/stageguard-learning-stage-transitions-for-long-horizon-robot-tasks-via-agentic-distillation.
Vancouver
Huang J, Hu Y, Li Z, Qi R, Xiao Y, Wu Y, et al. StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation. https://omanscience.com/en/articles/stageguard-learning-stage-transitions-for-long-horizon-robot-tasks-via-agentic-distillation
IEEE
J. Huang, Y. Hu, Z. Li, R. Qi, Y. Xiao, Y. Wu, T. Ba, Z. Zhang, and Y. Zhang, "StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation," https://omanscience.com/en/articles/stageguard-learning-stage-transitions-for-long-horizon-robot-tasks-via-agentic-distillation.