Author

Zhong-Zhi Li

Institutions: Microsoft (United States), Chinese Academy of Sciences, Institute of Automation, University of Chinese Academy of Sciences, University College of Applied Science

Observed institutions: Microsoft (United States), Chinese Academy of Sciences, Institute of Automation, University of Chinese Academy of Sciences, University College of Applied Science

OpenAlex ID: A5139816606

Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning

2026 · Zelin Tan, Hejia Geng, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting

Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability

2026 · Xiao Liang, Zhong-Zhi Li, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting

Too Long, Do Re-weighting for Efficient LLM Reasoning Compression

2026 · Zhong-Zhi Li, Xiao Liang, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting

Works count: 3

Citation count:

H-index:

I10-index: