# AgentDoG 1.5：一个轻量级且可扩展的AI智能体安全与安保对齐框架

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-28 08:00
- AIHOT 分数：62
- AIHOT 链接：https://aihot.virxact.com/items/cmpqd5x5k03y3slnogta5isvy
- 原文链接：https://arxiv.org/abs/2605.29801

## AI 摘要

AgentDoG 1.5是一个针对Codex和OpenClaw等现代开放世界智能体安全风险的轻量级、可扩展对齐框架。它更新了智能体安全分类法，构建了数据引擎，仅用约1k样本训练出0.8B至8B参数的模型变体，性能与GPT-5.4等闭源模型相当。该框架还构建了高效的训练环境，大幅降低部署开销，并可作为在线护栏进行实时安全审核。实验表明其在复杂交互场景中达到先进水平，所有模型和数据集均已开源。

## 正文

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.