Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model Cascade

[2608.14650] Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model Cascade Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2608.14650 (cs) [Submitted on 30 Jul 2026] Title: Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model Cascade Authors: Malo de Pastor View a PDF of the paper titled Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model Cascade, by Malo de Pastor View PDF HTML (experimental) Abstract: Existing adaptive-inference and world-action-model systems use cheap-stage outputs or predicted futures to allocate additional computation. We study a narrower question: under paired exact-reset physical outcomes, can a Medium-derived interface predict when switching to a separately frozen Full predictor improves task-specific decision loss enough to justify sequential overhead? Our contribution is a paired evaluation and audit protocol, not a new generic routing rule: all candidate actions are executed from the same reset state, Medium and Full act on the same candidate set and task, and their paired physical-loss difference defines the routing target. On a fresh PushT bank (V106; 1,600 states, 39 tasks, three checkpoint pairs), a frozen prediction-interface router lowers overhead-inclusive decision cost relative to standalone Medium, standalone Full, and a latency-advantaged task-only router. We then prospectively seal a second 1,600-state PushT confirmation (V107) against a stronger current-state control using the task, a dimension-matched projection of current DINO features, and all five candidate actions, with no DINO encoder latency charged. The prediction interface lowers priced physical decision cost by 0.002549 (state-clustered 95% interval [-0.002867, -0.002238]; one-sided 95% upper bound -0.002286), with negative effects for all three checkpoint pairs. A controlled-PyBullet audit independently supports a composite task-prediction-regime router. The sequential router remains slower than fixed policies, and its advantage is restricted to low compute prices. The evidence supports incremental routing information in the tested prediction interface beyond one deliberately favoured current-DINO control, but not causal sufficiency, compute saving, closed-loop value, or cross-family generality. Comments: 20 pages, 6 figures, 6 tables Subjects: Machine Learning (cs.LG) ; Robotics (cs.RO) Cite as: arXiv:2608.14650 [cs.LG] (or arXiv:2608.14650v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.14650 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Malo De Pastor [ view email ] [v1] Thu, 30 Jul 2026 18:35:13 UTC (515 KB) Full-text links: Access Paper: View a PDF of the paper titled Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model Cascade, by Malo de Pastor View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs cs.RO 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? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) 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

• Global prediction of extreme floods in ungauged watersheds#247137
• Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction#440355
• AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research#615184
• AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research#614217
• Towards a Statistical Understanding of Mixture-of-Experts#926416