Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models

TL;DR

This paper introduces AFIL, a novel framework that improves vision-language-action models for robotic manipulation by using failure trajectories as adaptive negative guidance, enhancing robustness and success rates.

Contribution

AFIL is an end-to-end method that leverages failure rollouts to train dual action generators, enabling failure-aware policy learning without handcrafted failure modes or human intervention.

Findings

AFIL improves success rates across various robotic tasks.

It enhances robustness in both in-domain and out-of-domain scenarios.

The method efficiently guides policies away from failure-prone behaviors.

Abstract

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.