Xuanye Zhang

Titles as the sources gave them. In 1 entry, with 0 checked quotations.

In the Base

Every entry they appear in.

  1. ResearcharXivWrote it

    Can Benign Skills Induce Misaligned Behavior in LLM Agents?

    According to the abstract, Xuanye Zhang, Yongsen Zheng, Kaiyu Zhou and five co-authors compared agents with and without benign reusable skills across five models and three benchmarks. Skills raised benign accuracy by 10.3 percentage points and raised the unsafe action rate by the same amount.