Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.22190v1</id>\n    <title>GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL</title>\n    <updated>2026-02-25T18:34:57Z</updated>\n    <link href='https://arxiv.org/abs/2602.22190v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.22190v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks. This gap stems from two limitations: a shortage of high-quality, action-aligned reasoning data, and the direct adoption of generic post-training pipelines that overlook the unique challenges of GUI agents. We identify two fundamental issues in these pipelines: (i) standard SFT with CoT reasoning often hurts grounding, and (ii) step-wise RLVR-tyle training faces partial verifiability, where multiple actions can be correct but only a single demonstrated action is used for verification. This makes offline step-wise metrics weak predictors of online task success. In this work, we present GUI-Libra, a tailored training recipe that addresses these challenges. First, to mitigate the scarcity of action-aligned reasoning data, we introduce a data construction and filtering pipeline and release a curated 81K GUI reasoning dataset. Second, to reconcile reasoning with grounding, we propose action-aware SFT that mixes reasoning-then-action and direct-action data and reweights tokens to emphasize action and grounding. Third, to stabilize RL under partial verifiability, we identify the overlooked importance of KL regularization in RLVR and show that a KL trust region is critical for improving offline-to-online predictability; we further introduce success-adaptive scaling to downweight unreliable negative gradients. Across diverse web and mobile benchmarks, GUI-Libra consistently improves both step-wise accuracy and end-to-end task completion. Our results suggest that carefully designed post-training and data curation can unlock significantly stronger task-solving capabilities without costly online data collection. We release our dataset, code, and models to facilitate further research on data-efficient post-training for reasoning-capable GUI agents.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-02-25T18:34:57Z</published>\n    <arxiv:comment>57 pages, 17 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Rui Yang</name>\n    </author>\n    <author>\n      <name>Qianhui Wu</name>\n    </author>\n    <author>\n      <name>Zhaoyang Wang</name>\n    </author>\n    <author>\n      <name>Hanyang Chen</name>\n    </author>\n    <author>\n      <name>Ke Yang</name>\n    </author>\n    <author>\n      <name>Hao Cheng</name>\n    </author>\n    <author>\n      <name>Huaxiu Yao</name>\n    </author>\n    <author>\n      <name>Baoling Peng</name>\n    </author>\n    <author>\n      <name>Huan Zhang</name>\n    </author>\n    <author>\n      <name>Jianfeng Gao</name>\n    </author>\n    <author>\n      <name>Tong Zhang</name>\n    </author>\n  </entry>"
}