Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
STaR: Sensitive Trajectory Regulation for Unlearning in Large Reasoning Models
Jingjing Zhou, Gaoxiang Cong, Li Su +1
Large Reasoning Models (LRMs) have advanced automated multi-step reasoning, but their ability to generate complex Chain-of-Thought (CoT) trajectories introduces severe privacy risk…
cs.AI2025
The Art of Tool Interface Design
Yunnan Wu, Paul Chen, Deshank Baranwal +2
We present an agentic framework, Thinker, which achieves state of art performance in challenging reasoning tasks for realistic customer service scenarios that involve complex busin…