AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
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) usi...
| Authors | Dongrui Liu, Yu Li, Zhonghao Yang et al. |
|---|---|
| Primary category | cs.AI |
| Published | 28 May 2026 |
| Last updated at source | 28 May 2026 |
Connected in the knowledge graph
- AI45Research/AgentDoG1.5-Qwen3.5-4BModel · cited by
- AI45Research/AgentDoG1.5-Qwen3.5-0.8BModel · cited by
- AI45Research/AgentDoG1.5-Qwen3.5-2BModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.