AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security Paper • 2605.29801 • Published May 28 • 150
AgentDoG1.5 Collection A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security • 11 items • Updated Jun 21 • 15
AgentDoG Collection A Diagnostic Guardrail Framework for AI Agent Safety and Security • 12 items • Updated Jun 21 • 112
Rethink_SFT_generalization Collection Repo for paper Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability. • 40 items • Updated Apr 11 • 21
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 330
RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback Paper • 2603.08561 • Published Mar 9 • 12
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security Paper • 2601.18491 • Published Jan 26 • 126
CineBrain: A Large-Scale Multi-Modal Brain Dataset During Naturalistic Audiovisual Narrative Processing Paper • 2503.06940 • Published Mar 10, 2025 • 11
