Machine Learning Algorithms & Natural Language Processing

Jun 7, 2026 · Artificial Intelligence

AgentDoG 1.5: A Lightweight, Extensible Framework for Trajectory‑Level Agent Safety

AgentDoG 1.5 expands AI‑agent safety from final replies to complete execution trajectories, introducing the ATBench family for fine‑grained evaluation, a taxonomy‑guided DataEngine for high‑quality data generation, and demonstrating substantial safety gains in both SFT/RL training and online guardrail deployment with lightweight models.