{"ID":5551602,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T15:13:22.648032999Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01060","arxiv_id":"2607.01060","title":"RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy Evaluation","abstract":"Video world models are emerging as a scalable alternative for evaluating generalist robot policies, bypassing the physical constraints and engineering burdens of real-world deployment. However, evaluating policies with video world models remains challenging, as world-model errors can make generated rollouts unreliable and slow inference limits large-scale throughput. We introduce RoboWorld, an automated evaluation pipeline that pairs a fast autoregressive video world model with a task-progress-aware vision-language model scoring. To enable reliable long-horizon autoregressive world-model rollouts, we propose Step Forcing, which combines anchored and one-step self-forwarded contexts to reduce train--test mismatch while preserving action--observation dynamics. Together, these components enable RoboWorld to align strongly with real-world robot evaluation across tasks and environments, achieving Pearson's r = 0.989 and Spearman's \\r{ho} = 0.970.","short_abstract":"Video world models are emerging as a scalable alternative for evaluating generalist robot policies, bypassing the physical constraints and engineering burdens of real-world deployment. However, evaluating policies with video world models remains challenging, as world-model errors can make generated rollouts unreliable...","url_abs":"https://arxiv.org/abs/2607.01060","url_pdf":"https://arxiv.org/pdf/2607.01060v1","authors":"[\"Byeongguk Jeon\",\"Seonghyeon Ye\",\"JaeHyeok Doo\",\"Sungdong Kim\",\"Minjoon Seo\",\"Hyungmok Son\",\"Kimin Lee\"]","published":"2026-07-01T15:22:41Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Language Model\"]","has_code":false}