Blogs
Research Blogs
2026
The Sim-to-Real Gap of Foundation Model Agents
KDD’26 Blue Sky · Xiaoou Liu*, Tiejin Chen*, Weibo Li, Xiyang Hu, Hua WeiDiagnosing Multi-step Reasoning Failures via Stepwise Confidence Attribution
ICML’26 · Xiaoou Liu, Tiejin Chen, Dengjia Zhang, Yaqing Wang, Lu Cheng, Hua Wei
2025
- Uncertainty Quantification & Confidence Calibration in LLMs: A Survey
KDD’25 Survey · Xiaoou Liu*, Tiejin Chen*, Longchao Da, Chacha Chen, Zhen Lin, Hua Wei
