Author

Wenkai Yang

Observed name: Yang, Wenkai

Institutions: DeepSeek (China), Renmin University of China

Observed institutions: DeepSeek (China), Renmin University of China

OpenAlex ID: A5129652014

Certified Multi-Turn Robustness for LLM Safety via Compositional Bounds and Safety Persistence

2026 · Liu, Yang, Chong, Bin, et al. · arXiv (Cornell University)

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

2026 · Cheng, Xin, Yu, Xingkai, et al. · arXiv (Cornell University)

Rethinking Continual Experience Internalization for Self-Evolving LLM Agents

2026 · Chen, Jingwen, Yang, Wenkai, et al. · arXiv (Cornell University)

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

2026 · Li, Yaxuan, Zuo, Yuxin, et al. · arXiv (Cornell University)

AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents

2026 · Fan, Shengda, Ye, Xuyan, et al. · arXiv (Cornell University)

Works count: 5

Citation count:

H-index:

I10-index: