Clarenceai

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

RLHF & Preference Learning (1)Scalable Oversight & Alignment Theory (1)

Frequent co-authors

Boyang Liu (1)Sen-Jie Jin (1)Peixin Wang (1)Zhangyue Yin (1)

Papers (1)

Aug 25, 2026

3d ago·also Affiliation:, Tencent AI

CAFE: Self-Improving Search Agents Need Co-Evolving Feedback

Self-improving search agents thrive when feedback and policy evolution are intertwined, leading to sustained performance gains and reduced hallucinations.

Boyang Liu, Sen-Jie Jin, Peixin Wang +13

RLHF & Preference Learning Scalable Oversight & Alignment Theory