Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 327
AgentDoG Collection A Diagnostic Guardrail Framework for AI Agent Safety and Security • 12 items • Updated May 12 • 112
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security Paper • 2601.18491 • Published Jan 26 • 126