EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control

[2605.21862] EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Robotics arXiv:2605.21862 (cs) [Submitted on 21 May 2026 ( v1 ), last revised 15 Aug 2026 (this version, v2)] Title: EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control Authors: Chushan Zhang , Ruihan Lu , Jinguang Tong , Xuesong Li , Yikai Wang , Hongdong Li View a PDF of the paper titled EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control, by Chushan Zhang and 5 other authors View PDF HTML (experimental) Abstract: Chunked vision-language-action (VLA) policies predict multi-step robot controls, conditioning each update on the current visual observation alone. Yet robot actions cause contact, occlusion, and object motion, and the geometry that later decisions depend on can change before the next visual update arrives. Spatial VLAs improve current-frame geometry. Temporal VLAs aggregate past frames. Neither maintains an action-updated scene prior across chunks. We argue for a persistent action-updated scene state across control calls, and introduce EvoScene-VLA. Its recurrent scene prefix carries a geometry-aware scene state across chunks. At each vision-language model (VLM) call, the VLM combines scene information from the current observation with the action-updated prior from the previous chunk; the action decoder outputs both the next action chunk and a compact scene update. This update becomes the next prior, which the VLM corrects against the new observation when the next call arrives. Each control call therefore starts from a scene prior that reflects both recent actions and fresh visual evidence. During training, \textbf{Scene Predictor} supplies future scene-token targets, and Geometric Anchor aligns scene slots with frozen depth and 3D teachers. We discard both modules at deployment. On 31 RoboTwin tasks, EvoScene-VLA raises average success from 87.2% to 89.1% in fixed evaluation and from 86.1% to 88.5% in randomized evaluation. On the Galaxea R1-Lite real robot, EvoScene-VLA outperforms all baselines. Subjects: Robotics (cs.RO) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2605.21862 [cs.RO] (or arXiv:2605.21862v2 [cs.RO] for this version) https://doi.org/10.48550/arXiv.2605.21862 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Chushan Zhang [ view email ] [v1] Thu, 21 May 2026 01:19:17 UTC (14,432 KB) [v2] Sat, 15 Aug 2026 07:42:38 UTC (19,141 KB) Full-text links: Access Paper: View a PDF of the paper titled EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control, by Chushan Zhang and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.RO < prev | next > new | recent | 2026-05 Change to browse by: cs cs.AI 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

• EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control#608883
• IMPACT-VLA: Interaction-aware Multimodal Propagation Attribution via Counterfactual Trajectories for Vision-Language-Action Policies#1084904
• InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policies#1064278
• HINT: Human-Intent Inception for Long-Horizon Robot Manipulation#973402
• Faster and Better? Benchmark Bugs and Design Limitations Distort the Evaluation of Vision-Language-Action Acceleration#1142080