{"ID":5552877,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-03T23:33:56.302496761Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00272","arxiv_id":"2607.00272","title":"ASPIRE: Agentic /Skills Discovery for Robotics","abstract":"Traditional robot programming is challenging: it requires orchestrating multimodal perception, managing physical contact dynamics, and handling diverse configurations and execution failures. We introduce ASPIRE (Agentic Skill Programming through Iterative Robot Exploration), a continual learning system that autonomously writes and refines robot control programs in a code-as-policy paradigm while compounding experience into a reusable skill library. ASPIRE discovers skills that persist across tasks, simulation and real-world settings, and embodiments. It operates in an open-ended loop with three components: (1) a closed-loop robot execution engine that exposes fine-grained multimodal traces, enabling autonomous failure diagnosis, repair synthesis, and validation; (2) a continually expanding skill library that distills validated fixes into reusable, transferable knowledge; and (3) evolutionary search that generates diverse task sequences and control programs to explore beyond single-trajectory refinement. ASPIRE surpasses prior methods by up to 77% on LIBERO-Pro manipulation under perturbation, 72% on Robosuite bimanual handover, and 32% on BEHAVIOR-1K long-horizon household tasks. Its accumulated library also enables zero-shot generalization to unseen long-horizon tasks: on LIBERO-Pro Long, ASPIRE achieves 31% success versus 4% for prior methods despite their use of test-time reasoning and retries. Finally, simulation-discovered skills provide initial evidence of sim-to-real transfer, substantially reducing real-robot programming effort across different embodiments and robot APIs.","short_abstract":"Traditional robot programming is challenging: it requires orchestrating multimodal perception, managing physical contact dynamics, and handling diverse configurations and execution failures. We introduce ASPIRE (Agentic Skill Programming through Iterative Robot Exploration), a continual learning system that autonomousl...","url_abs":"https://arxiv.org/abs/2607.00272","url_pdf":"https://arxiv.org/pdf/2607.00272v1","authors":"[\"Runyu Lu\",\"Yubo Wu\",\"Ethan Kou\",\"Letian Fu\",\"Wenli Xiao\",\"Ajay Mandlekar\",\"Yinzhen Xu\",\"Guanya Shi\",\"Ken Goldberg\",\"Ang Chen\",\"Mosharaf Chowdhury\",\"Yuke Zhu\",\"Linxi \\\"Jim\\\" Fan\",\"Guanzhi Wang\"]","published":"2026-06-30T23:38:46Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.MA\"]","methods":"[\"LoRA\"]","has_code":false}