We introduce OpenMobile-2, a near-frontier mobile agent with fully open training environments and recipes. We make three key advances: (1) Diverse environments with simulated commercial apps: We build MobileGym++, featuring 35 realistic, functionally rich commercial-style apps with cross-app workflows, while preserving...
Chen-Yang Yan, Ying-Ying Zhang, Kanzhi Cheng et al.· 0 citations
This work replaces true next-observation targets with in-distribution mismatched observations and introduces a setting that replaces prediction-based rewards with independent random signals, which expands task coverage even when the reward carries no environment information.
Xin-Yu Che, Hang Yan, Yan-Chen Liu et al.· 0 citations
This work introduces GameLogicBench, a benchmark of 72 gameplay-logic tasks in Godot projects, and compared versions of the benchmark evaluator built with and without validation using mutants.
Xin-Yu Che, Yun-Fei Ge, Shi-Hao Li et al.· 2 citations
An evaluation framework that holds candidate retrieval, target state, model, decoding, and tool budget fixed while varying the support delivered to the agent is formulated, separating retrieval quality from the problem of turning retrieved experience into safe, useful support for a new task.
Yifei Li, Heng Wang, Lingling Zhang et al.· 0 citations
Self-specialized teacher distillation (SSTD), a two-stage procedure that first trains a copy of the base model into a domain teacher, then distills its token distribution to a student on prefixes sampled from the student itself, is proposed.
Yifei Li, Rong-Man Xu, Lingling Zhang et al.· 1 citation
OSReward is introduced, a realistic, high-quality benchmark that evaluates VLM judges on CUA trajectories, and an open corpus of reasoning-annotated trajectory judgments for the CUA community, to close the gap in reliable CUA reward at scale.
Qiushi Sun, Kanzhi Cheng, Yian Wang et al.· arXiv.org· 1 citation· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
