Author

Ziqi Miao

View on Semantic Scholar

2 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 Sep 2026

Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents

This work proposes Defense-as-Skill, a defense paradigm that implements the runtime guard itself as an installable, inspectable, and editable skill, and demonstrates transfer across victim models, held-out risk families, and external benchmarks, as well as retained protection against adaptive attackers.

Xiao-Fan Yang, Ziqi Miao, Dianbo Sui et al. · 0 citations

Preprint Aug 2026

Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations

SCHEMA reveals that hallucinations concentrate at a small set of highly connected knowledge hubs, and that final-answer accuracy decouples from trajectory honesty; models often reach correct conclusions through structurally flawed reasoning.

Xinshun Feng, Ziqi Miao, Li-Jun Li et al. · 0 citations