AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Paper • 2605.29801 • Published • 134
AgentDoG1.5
A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
-
-
AI45Research/AgentDoG1.5-FG-Qwen3.5-0.8B
Text Classification • 0.9B • Updated • 51 • 1 -
AI45Research/AgentDoG1.5-Llama-3.1-8B
Text Classification • 8B • Updated • 40 -
AI45Research/AgentDoG1.5-FG-Qwen3.5-4B
Text Classification • 5B • Updated • 36 -
AI45Research/AgentDoG1.5-FG-Qwen3.5-2B
Text Classification • 2B • Updated • 43 • 1 -
AI45Research/AgentDoG1.5-Qwen3.5-2B
Text Classification • 2B • Updated • 44 -
AI45Research/AgentDoG1.5-FG-Llama-3.1-8B
Text Classification • 8B • Updated • 41 • 1 -
AI45Research/AgentDoG1.5-Qwen3.5-4B
Text Classification • 5B • Updated • 239 • 2 -
AI45Research/AgentDoG1.5-Qwen3.5-0.8B
Text Classification • 0.9B • Updated • 44 • 1 -
AI45Research/AgentDoG1.5-Unified-Qwen3.5-4B
Text Classification • 4B • Updated • 211 • 2