Dong Li
Scholar

Dong Li

Google Scholar ID: U_LFSV4AAAAJ
Huawei Noah's Ark Lab
Reinforcement learningLLM Alignment
Google Scholar↗
Citations & Impact
All-time
Citations
1,783
 
H-index
24
 
i10-index
43
 
Publications
20
 
Co-authors
9
list available
Contact
No contact links provided.
Publications
6 items
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
Ratio-Variance Regularized Policy Optimization for Efficient LLM Fine-tuning
arXiv.org · 2026
Cited
0
Resume (English only)
Co-authors
9 total
Dongbin Zhao
Dongbin Zhao
Institute of Automation, Chinese Academy of Sciences
Qichao Zhang
Qichao Zhang
中国科学院自动化研究所
Weixun Wang
Weixun Wang
Alibaba
Hongyao Tang
Hongyao Tang
Mila/UdeM
Kun Shao
Kun Shao
Huawei
Co-author 6
Co-author 6
Yuanheng Zhu
Yuanheng Zhu
Institute of Automation, Chinese Academy of Sciences
Bin Wang
Bin Wang
Huawei Noah's Ark Lab