YW
Yite Wang
cs.AIcs.CLcs.LGstat.MLcs.CV
On Valency
published · living versionsW_swcb792r·v1 · currentpublished
Agent World Model in the Wild: Computer-Use Agent Environment Synthesis
with Zhaoyang Wang, Qianhui Wu, Haorui Wang, Simon Yu +7
1 version
Preprints & journals
11 papers in the corpus · 2022–2026Agent World Model in the Wild: Computer-Use Agent Environment Synthesis2610.26828v1 · Zhaoyang Wang, Qianhui Wu, Haorui Wang et al.2026 · 0 citationsarXivon Valency
Arctic-SWE: Revisiting the Long Horizon Agent Training by Modeling-System Co-Design2610.24914v1 · Boyi Liu, Yite Wang, Xinyu Lian et al.2026 · 0 citationsarXiv
Benchmarking Hybrid Deep Research Across Database Querying and Web Search2609.09410v1 · Ruofan Wu, Peiran Xu, Xiaolong Li et al.2026 · 0 citationsarXiv
MidTool: Mid-training Data Synthesis for Agentic Tool Use2608.20314v1 · Fengqing Jiang, Yite Wang, Boyi Liu et al.2026 · 0 citationsarXiv
The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows2608.06714v2 · Junbo Li, Boyi Liu, Canwen Xu et al.2026 · 0 citationsCOLM 2026
Learning to Self-Evolve2603.18620v1 · Xiaoyin Chen, Canwen Xu, Yite Wang et al.2026 · 0 citationsarXiv
DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science2602.24288v1 · Fan Shu, Yite Wang, Ruofan Wu et al.2026 · 1 citationarXiv
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning2602.10090v3 · Zhaoyang Wang, Canwen Xu, Boyi Liu et al.2026 · 0 citationsarXiv
LEMON: Lossless model expansion2310.07999v1 · Yite Wang, Jiahao Su, Hanlin Lu et al.2023 · 4 citationsarXiv
NTK-SAP: Improving neural network pruning by aligning training dynamics2304.02840v1 · Yite Wang, Dawei Li, Ruoyu Sun2023 · 4 citationsarXiv
Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning2203.09137v1 · Haoxiang Wang, Yite Wang, Ruoyu Sun et al.2022 · 40 citationsarXiv
Career total: 11 works. 11 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.