Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.08434 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914559283953664 |
|---|---|
| author | Zheng, Meng Marri, Samhita Choudhuri, Anwesa Planche, Benjamin Gao, Zhongpai Nguyen, Van Nguyen Chen, Terrence Chowdhary, Girish Wu, Ziyan |
| author_facet | Zheng, Meng Marri, Samhita Choudhuri, Anwesa Planche, Benjamin Gao, Zhongpai Nguyen, Van Nguyen Chen, Terrence Chowdhary, Girish Wu, Ziyan |
| contents | Vision-language-action (VLA) models provide a promising paradigm for scalable robotic manipulation, yet their reliance on success-only behavioral cloning leaves them brittle; lacking corrective training signals, minor execution errors rapidly compound into unrecoverable, out-of-distribution failures. To address this limitation, we propose Adaptive Failure-Informed Learning (AFIL), an end-to-end framework that leverages failure trajectories as adaptive negative guidance for diffusion- and flow-based VLA policies. AFIL uses a pretrained VLA to generate failure rollouts online, avoiding the need for handcrafted failure-mode design or human-in-the-loop recovery. It then jointly trains Dual Action Generators (DAGs) for successful and failed behaviors while sharing a common vision-language backbone, enabling efficient failure-aware policy learning with limited parameter overhead. During sampling, the failure generator adaptively steers action generation away from failure-prone regions and toward more reliable success modes, with guidance strength determined by the per-diffusion-step distance between success and failure distributions. Experiments across in-domain and out-of-domain robotic manipulation tasks, covering both short- and long-horizon settings, show that AFIL consistently improves task success rates and robustness over existing VLA baselines, demonstrating its effectiveness, efficiency, and generality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_08434 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models Zheng, Meng Marri, Samhita Choudhuri, Anwesa Planche, Benjamin Gao, Zhongpai Nguyen, Van Nguyen Chen, Terrence Chowdhary, Girish Wu, Ziyan Robotics Vision-language-action (VLA) models provide a promising paradigm for scalable robotic manipulation, yet their reliance on success-only behavioral cloning leaves them brittle; lacking corrective training signals, minor execution errors rapidly compound into unrecoverable, out-of-distribution failures. To address this limitation, we propose Adaptive Failure-Informed Learning (AFIL), an end-to-end framework that leverages failure trajectories as adaptive negative guidance for diffusion- and flow-based VLA policies. AFIL uses a pretrained VLA to generate failure rollouts online, avoiding the need for handcrafted failure-mode design or human-in-the-loop recovery. It then jointly trains Dual Action Generators (DAGs) for successful and failed behaviors while sharing a common vision-language backbone, enabling efficient failure-aware policy learning with limited parameter overhead. During sampling, the failure generator adaptively steers action generation away from failure-prone regions and toward more reliable success modes, with guidance strength determined by the per-diffusion-step distance between success and failure distributions. Experiments across in-domain and out-of-domain robotic manipulation tasks, covering both short- and long-horizon settings, show that AFIL consistently improves task success rates and robustness over existing VLA baselines, demonstrating its effectiveness, efficiency, and generality. |
| title | Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models |
| topic | Robotics |
| url | https://arxiv.org/abs/2605.08434 |