Kan Yu
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces MalSkills, a neuro-symbolic framework that detects malicious skills in the expanding agentic supply chain by analyzing security-sensitive operations across heterogeneous artifacts.
The paper investigates the limits of self-evolution in LLM reasoning under closed-loop settings, finding that while self-improvement is significant, it consistently falls short of perfect oracle supervision.
Papers
On the Generalization Gap in Self-Evolving Language Model Reasoning
Zhenting Qi, Susanna Maria Baby, Stefanie Anna Baby, Kan Yuan +4 more
The paper investigates the limits of self-evolution in LLM reasoning under closed-loop settings, finding that while self-improvement is significant, it consistently falls short of perfect oracle super…