2 papers
cs.AI2026
TRACE: An Evidence-Grounded Benchmark for Safety Evaluation of Large Reasoning Models
Zhenyu Wu, Siyuan Chen, Changchun Yang +8
Large Reasoning Models (LRMs) generate intermediate reasoning traces that may contain unsafe content, even when their final responses appear safe. Guardrail models are designed to…
cs.SE2026
A Survey of LLM-Driven Penetration Testing: Taxonomy, Co-Evolution, and Open Challenges
Zheyuan He, Jiaxun Dong, Zihao Li +6
Agents4Pentest, an emerging class of LLM-based autonomous penetration testing systems, has become a rapidly growing area in security research. Despite this growth, the field still…