This work argues that agentic risk is progressive: it can enter at four loci of the agent control loop--skill admission, invocation-time intent, execution-time effect, and post-action consequence--while a denied dangerous objective can reappear across surface forms, tools, or turns.
Kai Wang, Zeming Wei, Biaojie Zeng et al.· 0 citations
This work formulates student reasoning as a multi-step sequential decision problem and introduces Monte Carlo Tree Search (MCTS) to explore optimal correction paths and proposes a dual evaluation protocol centered on solution accuracy and correct-step retention, offering a comprehensive measure of educational applicability.
Biaojie Zeng, Min Zhang, Juan Zhou et al.· arXiv.org· 0 citations
This work presents SkillSafetyBench, a runnable benchmark for evaluating skill-facing safety failures, and suggests that agent safety depends not only on model-level alignment, but also on how agents interpret skills, trust workflow context, and act through executable environments.
