Author

Philip S. Yu

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

Evolving Together, Failing Apart: The Skill-Policy Co-evolution Trap in Self-Improving Agents

Skill-policy co-evolution, in which an agent's policy model and its skill bank improve each other during training, is a promising paradigm for self-improving agents. Current evaluations score the co-evolved policy on the final bank it trained with (the delivered bank). After deployment, however, skills may be rewritten...

Yu-Jie Feng, Xiao-Bin Wang, Jin-Luan Yang et al. · 0 citations

Preprint Aug 2026

Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update

The results suggest that anti-sycophancy should be treated not as a simple suppression problem, but as a selectivity problem, where effective interventions should preserve Rational-Updating while reducing Unsupported-Yielding.

Huanhuan Ma, Henry Peng Zou, Cheng-Ze Li et al. · 2 citations · ⚡1

Preprint Aug 2026

Online Test-Time Adaptation for Generalizable Dynamic Graph Anomaly Detection

Online test-time adaptation for generalizable DGAD is formulated and a proposed OTTA-DGAD, which selectively retains general patterns shared across the source domains used for pretraining while incorporating new patterns from the target domain.

Jialun Zheng, Han-Chen Yang, Jiannong Cao et al. · 0 citations