← Back to all news
arXiv AI By Yan Zhang, Daiqing Wu, Huawen Shen, Liang Li, Gang Cao, Zhi Gong, Wei Dai, Xiaode Zhang, Can Ma, Yu Zhou

Learn How to Act from Your Own Interactions: On-Policy Self-Distillation for GUI Agents

Read the original on arXiv AI →

The paper introduces GUI‑SD‑v2, an on‑policy self‑distillation framework that extends previous methods from GUI grounding to multi‑turn GUI interaction. It employs a two‑stage training process that first improves privilege following by jointly optimizing rollouts with and without privileged guidance, then selectively distills step‑specific reasoning and memory guidance via a privilege‑conditioned self‑teacher. Experiments on AndroidWorld and MobileWorld benchmarks demonstrate that GUI‑SD‑v2 outperforms existing OPSD baselines and state‑of‑the‑art methods in Pass@1 and Pass@3 success rates.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 17

Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents

The paper introduces EvoSkill-GUI, a training‑free framework that enables GUI agents to evolve their skills during deployment. Each skill is packaged with metadata, executable plans, and recovery rules, and the system follows a reflect‑revise‑reuse loop where the agent instantly revises skills based on execution feedback. Experiments on MobileWorld, AndroidWorld, and OSWorld show consistent performance gains up to +16.2% without any additional training.

By Bofan Chen, Boxuan Zhang, Fei Tang, Zhengxi Lu, Yong Du, Tongbo Chen, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen
agentsbenchmarks
More like this →
Hugging Face Trending Papers
Sep 24

From Self-Distillation to Self-Practice: Privileged Information for Multi-Turn Agents

The paper examines on‑policy self‑distillation (OPSD) for multi‑turn agents, showing that using privileged information (PI) in the loss can make agents appear confident yet underperform plain RL, sometimes worse than the untrained base model. To address this, the authors propose Privileged Self‑Practice (PSP), which keeps PI in the prompt and uses it only during sampling, not in the loss. PSP consistently outperforms plain GRPO across AppWorld and SWE‑bench Verified, improving task‑goal completion by up to 65% and resolved rate by up to 61%.

llmsagentsreinforcement-learningefficiency
More like this →