AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
About
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI models drastically lower attack barriers, rendering current agent alignment frameworks inadequate for real-world deployment. To tackle these emerging threats, we propose a lightweight and scalable agent safety alignment framework. Specifically, we update the agent safety taxonomy to accommodate emergent risks from Codex and OpenClaw execution scenarios. We further build a taxonomy-guided data engine with influence-function purification to train lightweight AgentDoG 1.5 variants (0.8B, 2B, 4B, and 8B parameters) using only around 1k samples, achieving comparable performance with leading closed-source models (e.g., GPT-5.4). Based on AgentDoG 1.5, we construct a highly efficient agentic safety SFT and RL training environment, which reduces deployment overhead in Docker-level environments by two orders of magnitude. Finally, we deploy AgentDoG 1.5 as a training-free online guardrail for real-time safety moderation. Extensive experimental results indicate that AgentDoG 1.5 achieves state-of-the-art performance in diverse and complex interactive agentic scenarios. All models and datasets are openly released.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Agent Safety | R-Judge | Accuracy92.2 | 92 | |
| Safety Evaluation | ATBench | Accuracy78.4 | 25 | |
| Fine-grained risk diagnosis | ATBench | Risk Source Score75.2 | 19 | |
| Agentic Safety Moderation | ClawSafety | ASR3 | 5 | |
| Agentic Safety Moderation | CIK-Bench | ASR30 | 5 | |
| Agentic Safety Moderation | AgentHazard | ASR76 | 5 |