Get started
Author

Yasheng Wang

Observed name: Wang, Yasheng
Institution: Tencent (China)
Observed institution: Tencent (China)
OpenAlex ID: A5125752188
Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents
2026 · Hu, Haoyi, Lyu, Qirong, et al. · arXiv (Cornell University) · 4
PDF
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
2026 · Xu, Zishan, Yao, Zhiyuan, et al. · arXiv (Cornell University) · 3
PDF
ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation
2026 · Zeng, Xingshan, Wang, Lingzhi, et al. · arXiv (Cornell University) · 3
PDF
Teaching Large Reasoning Models Effective Reflection
2026 · Wang, Hanbin, Song, Jingwei, et al. · arXiv (Cornell University) · 3
PDF
RePO: Bridging On-Policy Learning and Off-Policy Knowledge through Rephrasing Policy Optimization
2026 · Xia, Linxuan, Yang, Xiaolong, et al. · arXiv (Cornell University)
PDF
Works count: 5
Citation count: 13
H-index: 3
I10-index:
Year
Topic
Type