2 papers
cs.CR2026
Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking
Junke Zhang, Jianwei Wang, Sishuo Chen +3
Jailbreak attacks on large language models (LLMs) aim to induce LLMs to produce content that they are expected to refuse. Automated black-box jailbreak generation is important for…
cs.AI2026
CAX-Agent: A Lightweight Agent Harness for Reliable APDL Automation
Chenying Lin, Yichen Hai, Yi He +3
Large language models deployed for MAPDL finite-element simulation face practical reliability challenges: without structured execution control, tool encapsulation, and fault recove…