{"ID":23507443,"CreatedAt":"2026-09-18T02:21:44.056544415Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.20791","arxiv_id":"2609.20791","title":"StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation","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.","short_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 r...","url_abs":"https://arxiv.org/abs/2609.20791","url_pdf":"https://arxiv.org/pdf/2609.20791v1","authors":"[\"Jinbang Huang\",\"Yuanzhao Hu\",\"Zhiyuan Li\",\"Ran Qi\",\"Yixin Xiao\",\"Yangzheng Wu\",\"Tengyue Ba\",\"Zhanguang Zhang\",\"Yingxue Zhang\"]","published":"2026-09-17T17:53:48Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Language Model\"]","has_code":false}