{"ID":2873141,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.07953","arxiv_id":"2509.07953","title":"RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction","abstract":"Modern paradigms for robot imitation train expressive policy architectures on large amounts of human demonstration data. Yet performance on contact-rich, deformable-object, and long-horizon tasks plateau far below perfect execution, even with thousands of expert demonstrations. This is due to the inefficiency of existing ``expert'' data collection procedures based on human teleoperation. To address this issue, we introduce RaC, a new phase of training on human-in-the-loop rollouts after imitation learning pre-training. In RaC, we fine-tune a robotic policy on human intervention trajectories that illustrate recovery and correction behaviors. Specifically, during a policy rollout, human operators intervene when failure appears imminent, first rewinding the robot back to a familiar, in-distribution state and then providing a corrective segment that completes the current sub-task. Training on this data composition expands the robotic skill repertoire to include retry and adaptation behaviors, which we show are crucial for boosting both efficiency and robustness on long-horizon tasks. Across three real-world bimanual control tasks: shirt hanging, airtight container lid sealing, takeout box packing, and a simulated assembly task, RaC outperforms the prior state-of-the-art using 10$\\times$ less data collection time and samples. We also show that RaC enables test-time scaling: the performance of the trained RaC policy scales linearly in the number of recovery maneuvers it exhibits. Videos of the learned policy are available at https://rac-scaling-robot.github.io/.","short_abstract":"Modern paradigms for robot imitation train expressive policy architectures on large amounts of human demonstration data. Yet performance on contact-rich, deformable-object, and long-horizon tasks plateau far below perfect execution, even with thousands of expert demonstrations. This is due to the inefficiency of existi...","url_abs":"https://arxiv.org/abs/2509.07953","url_pdf":"https://arxiv.org/pdf/2509.07953v1","authors":"[\"Zheyuan Hu\",\"Robyn Wu\",\"Naveen Enock\",\"Jasmine Li\",\"Riya Kadakia\",\"Zackory Erickson\",\"Aviral Kumar\"]","published":"2025-09-09T17:41:29Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.LG\"]","methods":"[]","has_code":false}