StructRL: Structured Action-Space Exploration for Flow-Based VLAs

[2608.15139] StructRL: Structured Action-Space Exploration for Flow-Based VLAs Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Robotics arXiv:2608.15139 (cs) [Submitted on 15 Aug 2026] Title: StructRL: Structured Action-Space Exploration for Flow-Based VLAs Authors: Jiarui Yang , Bin Zhu , Jingjing Chen , Na Zou , Yanwei Fu , Jianggang Zhu , Yu-Gang Jiang View a PDF of the paper titled StructRL: Structured Action-Space Exploration for Flow-Based VLAs, by Jiarui Yang and 6 other authors View PDF HTML (experimental) Abstract: Flow-based Vision-Language-Action (VLA) models are now widely used for continuous robotic manipulation, and online reinforcement learning (RL) is emerging as a key technique for adapting them to new tasks. Existing RL methods typically inject stochasticity inside the denoising chain, often through isotropic or temporally independent noise. However, effective robot exploration calls for structured noise: temporally smooth and scaled differently across action groups. We show that simply switching the in-chain noise to a structured form does not suffice: noise added at an intermediate flow time can be weakened by the remaining denoising steps before execution, a phenomenon we call \emph{Structured Noise Dilution}. We propose \textbf{StructRL}, which avoids dilution by relocating policy stochasticity to the action space via three coupled choices: (i) a deterministic ODE decoder, (ii) structured noise injected directly in the action space, and (iii) last-step replay, where policy-gradient updates avoid assigning likelihoods to intermediate denoising states. This keeps structured exploration tied to the executed action while providing a tractable training signal for the flow decoder. Across three flow-based VLA models on multiple simulated manipulation benchmarks and two real-world tasks, StructRL improves exploration efficiency and OOD performance over prior in-chain baselines, demonstrating the effectiveness of structured action-space exploration for adapting flow-based VLA with RL. \textbf{Project page:} this https URL Subjects: Robotics (cs.RO) Cite as: arXiv:2608.15139 [cs.RO] (or arXiv:2608.15139v1 [cs.RO] for this version) https://doi.org/10.48550/arXiv.2608.15139 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Jiarui Yang [ view email ] [v1] Sat, 15 Aug 2026 09:31:29 UTC (3,695 KB) Full-text links: Access Paper: View a PDF of the paper titled StructRL: Structured Action-Space Exploration for Flow-Based VLAs, by Jiarui Yang and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.RO < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark 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? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• StructRL: Structured Action-Space Exploration for Flow-Based VLAs#611088
• SMILE: Smooth Motion for Improved Long-Horizon VLA Execution#794222
• SMILE: Smooth Motion for Improved Long-Horizon VLA Execution#790203
• Online Evolution Strategy for Flow-Matching VLA Policies via Self-Supervised Trajectory Distribution Optimization#1143456
• Code in Space: How Multimodal Human-AI Experience Can Reshape the Future of Tech Creation#1070975