All Quiet on the Neural Front: Language Models Do Not Report Injected Pain States Paper • 2611.10123 • Published 14 days ago • 7
The Butterfly Effect in LLM Social Simulations: From Architecture Sensitivity to Robustness Audits Paper • 2610.28981 • Published Oct 20
Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems Paper • 2610.30418 • Published about 1 month ago • 21