Skip to content
AI News HubLIVE
Original source2 min read

RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA Policy

Summary

RedFlow is a fine-grained offline RL framework that converts failure experiences into action-level corrective supervision for flow-matching VLA policies, improving real-world success rate from 56.7% to 74.7% with an order of magnitude fewer training samples than on-policy methods.

SourcearXiv RoboticsAuthor: Zhengyang Yan, Junhao Li, Fangqi Zhu, Zijun Wang, Quanxin Shou, Yikun Miao, Xiaoyi Pang, Zicong Hong, Song Guo
RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA Policy
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 30 Jul 2026]

Title:RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA Policy

View a PDF of the paper titled RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA Policy, by Zhengyang Yan and 8 other authors

View PDF HTML (experimental)

Abstract:Flow-matching Vision-Language-Action (VLA) policies have shown strong potential for robotic manipulation but often suffer from compounding errors caused by distribution shifts during deployment. While offline reinforcement learning (RL) provides a practical way to improve deployed policies using rollout data, existing methods either ignore failure data or exploit it only at the trajectory level, resulting in low learning efficiency and persistent errors. We propose RedFlow, a fine-grained offline RL framework that redirects failure experiences into action-level corrective supervision for flow-matching VLA policies. RedFlow consists of two key components: (1) a Context-Aware Corrective Matching mechanism that identifies failure-inducing actions and retrieves successful alternatives from similar contexts as corrective targets, and (2) an Adaptive Redirection Objective that jointly reinforces successful actions, suppresses undesirable ones, and redirects recoverable failures toward corrective targets. By converting both successful and failed experiences into dense supervision, RedFlow enables robust recovery learning from mixed-quality data. Experiments on the LIBERO benchmark and three real-world manipulation tasks show that RedFlow consistently outperforms state-of-the-art offline RL baselines, improving the real-world success rate from 56.7% to 74.7%. It also matches strong on-policy methods (PPO, GRPO, and DDPO) while requiring roughly an order of magnitude fewer training samples.

Subjects:

Robotics (cs.RO); Artificial Intelligence (cs.AI)

Cite as: arXiv:2607.27782 [cs.RO]

(or arXiv:2607.27782v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2607.27782

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Zhengyang Yan [view email] [v1] Thu, 30 Jul 2026 07:14:39 UTC (8,061 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA Policy, by Zhengyang Yan and 8 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-07

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • RedFlow redirects failure data into dense action-level supervision instead of trajectory-level exploitation.
  • Achieves 74.7% real-world success rate, up from 56.7%, on three manipulation tasks.
  • Matches PPO, GRPO, and DDPO while using roughly 10x fewer training samples.

Highlights and analysis are generated automatically and may contain errors. Check the original source.