Scholar
Yu Li
Google Scholar ID: gCoIftIAAAAJ
Salesforce Research
Dialog Systems
Natural Language Processing
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
890
H-index
12
i10-index
15
Publications
20
Co-authors
16
list available
Publications
8 items
Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps
2026
Cited
0
Fork Where the Model Changes Its Mind: Belief-Shift Branching for Tree-Structured Reinforcement Learning
2026
Cited
0
On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification
2026
Cited
0
Best Friends, Not Forever: Evaluating Long-Horizon Persona Collapse and Behavioral Drift in AI Companions
2026
Cited
0
Speculate with Memory: Lossless Acceleration for LLM Agents
2026
Cited
0
Dont Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination
2026
Cited
0
InterviewSim: A Scalable Framework for Interview-Grounded Personality Simulation
2026
Cited
0
The Need for a Socially-Grounded Persona Framework for User Simulation
arXiv.org · 2026
Cited
0
Co-authors
15 total
Zhou Yu
Columbia University
Weiyan Shi
Northeastern University
Jianfeng Gao
Microsoft Research, Redmond
Baolin Peng
Microsoft Research, Redmond
Qingyang Wu
Together AI
Kun Qian
Columbia University
Lars Liden
Microsoft Research
Mingyang Zhou
Applied Researcher, Capital One
