الباحثون

Zhangchen Xu

المنشورات 2

نسخة أولية وصول مفتوح

SecProbe: Adaptive Evaluation of Coding Agents on Cybersecurity Vulnerabilities

Xiaonan Luo, Yue Huang, Kehan Guo وآخرون · 2026

Assessing cybersecurity vulnerability awareness in coding agents requires evaluations that reveal capability gaps and remain informative as models evolve. Static benchmarks offer fixed coverage and difficulty, while scarce vulnerable repositories and costly expert authoring limit their renewal at scale. We introduce Se …

نسخة أولية وصول مفتوح

Reward Hacking Challenges Oversight of Autonomous Research Agents

Yue Huang, Zhangchen Xu, Yuchen Ma وآخرون · 2026

Autonomous research agents can design experiments, evaluate results, and write reports, giving them control over both a scientific result and the evidence used to support it. This creates a risk of reward hacking: meeting the reward criteria without achieving the intended goal. We study (1) how often models reward-hack …

المؤلفون المشاركون