Paper Detail

CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies

Junlan Xiao, Junwei Jiang, Zaibin Zhang, Yifan Wang, Zhongbo Zhang, Huchuan Lu, Lijun Wang

huggingface Score 12.5

Published 2026-09-21 · First seen 2026-09-22

General AI

Abstract

Vision-Language-Action (VLA) policies achieve strong performance in robotic manipulation but remain brittle once execution deviates from nominal trajectories. We propose CARE (Corrective Atomic Robotic Execution), a framework that improves recovery by learning from failures encountered during execution. Instead of generating corrective data from manually designed or random perturbations, CARE collects failed rollouts, models stage-conditioned post-failure deviations, and uses the resulting empirical distributions to synthesize representative failure states and corrective demonstrations. At inference time, CARE combines stage-wise planning with physically grounded 3D monitoring to trigger atomic adjustments or re-operations while preserving task progress. We further introduce the Failure State Recovery Benchmark (FSR-Bench), which evaluates recovery from intermediate failure states under local deviations and structural anomalies. Experiments across multiple VLA backbones, simulation benchmarks, and real-world dual-arm tasks show consistent improvements, with average task-success gains of 14.5 points in simulation and 15.9 points in the real world. Code, models, and data are available at https://github.com/xiaojunlan/care

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{xiao2026care,
  title = {CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies},
  author = {Junlan Xiao and Junwei Jiang and Zaibin Zhang and Yifan Wang and Zhongbo Zhang and Huchuan Lu and Lijun Wang},
  year = {2026},
  abstract = {Vision-Language-Action (VLA) policies achieve strong performance in robotic manipulation but remain brittle once execution deviates from nominal trajectories. We propose CARE (Corrective Atomic Robotic Execution), a framework that improves recovery by learning from failures encountered during execution. Instead of generating corrective data from manually designed or random perturbations, CARE collects failed rollouts, models stage-conditioned post-failure deviations, and uses the resulting empir},
  url = {https://huggingface.co/papers/2609.24118},
  keywords = {code available, huggingface daily},
  eprint = {2609.24118},
  archiveprefix = {arXiv},
}

Metadata

{}