5 papers
Less Sycophancy, Stronger Refusal? Lessons for AI Safety from Mechanistic Interpretability
Xu Wang, Difan Zou, Xuansheng Wu
Reliable refusal of harmful requests is essential to the safe deployment of language models. Because excessive eagerness to please users may undermine existing refusal capabilities…
Agent Skills Matter: Inferring Proprietary Skills from Execution Trajectories
Jianing Geng, Ruiqi He, Zekun Fei +6
Agent skills package reusable procedures that improve downstream performance. Their lightweight, portable form enables marketplace monetization and private deployment behind cloud-…
Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence
Xinquan Chen, Zhenyun Yin, Shan He +38
As large models evolve from conversational assistants into autonomous agents, challenges increasingly arise from long-horizon decision making, tool use, and real environment intera…
Investigating CoT Monitorability in Large Reasoning Models
Shu Yang, Junchao Wu, Xilin Gong +4
Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex tasks by engaging in extended reasoning before producing final answers. Beyond improving abilities…
Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs
Shu Yang, Junchao Wu, Xuansheng Wu +3
Large Reasoning Models (LRMs) have achieved remarkable performance on complex tasks by engaging in extended reasoning before producing final answers, yet this strength introduces t…