ZD
Zichen Ding
cs.CLcs.AIcs.CVcs.HCcs.LGcs.MA
On Valency
published · living versionsW_ffw4e4ww·v1 · currentpublished
OS-Wizard: Scaling Computer-Using Agents to Specialized Software via Knowledge-Guided Exploration
with Zhoumianze Liu, Bowen Yang, Zehao Li, Zhenyu Wu +6
1 version
Preprints & journals
13 papers in the corpus · 2024–2026OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models2607.28609v2 · Qiushi Sun, Kanzhi Cheng, Yian Wang et al.2026 · 0 citationsarXiv
MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop2606.22557v1 · Yikun Fu, Bowen Fu, Zhenyu Wu et al.2026 · 0 citationsarXiv
Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents2605.30723v1 · Jianxiang Yu, Jiapeng Zhu, Bochen Lin et al.2026 · 0 citationsarXiv
OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis2604.15093v1 · Kanzhi Cheng, Zehao Li, Zheng Ma et al.2026 · 0 citationsarXiv
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale2603.25040v2 · Yicheng Zou, Dongsheng Zhu, Lin Zhu et al.2026 · 1 citationarXiv
OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards2603.19191v1 · Zehao Li, Zhenyu Wu, Yibo Zhao et al.2026 · 0 citationsarXiv
TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents2602.02196v2 · Hang Yan, Xinyu Che, Fangzhi Xu et al.2026 · 0 citationsarXiv
OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent2601.07779v1 · Bowen Yang, Kaiming Jin, Zhenyu Wu et al.2026 · 0 citationsarXiv
GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence2601.04525v1 · Yibo Zhao, Jiapeng Zhu, Zichen Ding et al.2026 · 0 citationsarXiv
ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data2509.15221v2 · Zhaoyang Liu, Jingjing Xie, Zichen Ding et al.2025 · 0 citationsarXiv
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis2412.19723v3 · Qiushi Sun, Kanzhi Cheng, Zichen Ding et al.2024 · 7 citationsarXiv
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents2410.23218v1 · Zhiyong Wu, Zhenyu Wu, Fangzhi Xu et al.2024 · 0 citationsarXiv
OS-Copilot: Towards Generalist Computer Agents with Self-Improvement2402.07456v2 · Zhiyong Wu, Chengcheng Han, Zichen Ding et al.2024 · 6 citationsarXiv
Career total: 14 works. 13 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.