Scholar
Dong Li
Google Scholar ID: U_LFSV4AAAAJ
Huawei Noah's Ark Lab
Reinforcement learning
LLM Alignment
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
1,783
H-index
24
i10-index
43
Publications
20
Co-authors
9
list available
Publications
9 items
Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning
2026
Cited
0
Ratio-Variance Regularized Policy Optimization
2026
Cited
0
When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling
2026
Cited
0
When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning
2026
Cited
0
$\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving
2026
Cited
0
PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning
2026
Cited
0
JEPA-VLA: Video Predictive Embedding is Needed for VLA Models
2026
Cited
0
ASTER: Agentic Scaling with Tool-integrated Extended Reasoning
2026
Cited
0
Load more
Co-authors
8 total
Dongbin Zhao
Institute of Automation, Chinese Academy of Sciences
Qichao Zhang
中国科学院自动化研究所
Weixun Wang
Alibaba
Hongyao Tang
Mila/UdeM
Kun Shao
Huawei
Yuanheng Zhu
Institute of Automation, Chinese Academy of Sciences
Bin Wang
Huawei Noah's Ark Lab
Wulong Liu
Unknown affiliation
