Saved in:
Bibliographic Details
Main Authors: Zheng, Meng, Marri, Samhita, Choudhuri, Anwesa, Planche, Benjamin, Gao, Zhongpai, Nguyen, Van Nguyen, Chen, Terrence, Chowdhary, Girish, Wu, Ziyan
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