SEA-LION 发布 Gemma-SEA-LION-Guard-v2 安全护栏模型，提供 31B、E4B、E2B 三个规格
Safeguarding Regional Agents: Announcing Gemma-SEA-LION-Guard-v2 (31B, E4B, E2B)
新加坡 AI Singapore 团队出了个专门管 Agent 安全的护栏模型，能做多轮审查和自定义策略，还有三个尺寸可以按算力选。
AI Singapore 的 SEA-LION 项目发布 Gemma-SEA-LION-Guard-v2，基于 Gemma4 模型，提供 31B、E4B、E2B 三个规格。新版本面向多轮环境中的自主智能体，引入 Action Governance（行动治理）、Multi-Turn Evaluation（多轮评估）和自定义策略执行能力。传统审核模型主要针对单轮安全分类，难以应对涉及区域语境的隐蔽风险，该模型据此针对性改进。官方还以 Jev-style Prediction 的方式说明了其部署思路。
Safeguarding Regional Agents: Announcing Gemma-SEA-LION-Guard-v2 (31B, E4B, E2B)
Advancing AI Safety with Action Governance, Multi-Turn Evaluation, and Custom Policy Enforcement – Jev-style Prediction, Powered by Gemma4 Models As AI agents transition from simple conversational chatbots into autonomous tools operating in complex, multi-turn environments, safety guardrails must evolve alongside them. Traditional moderation models—designed primarily for single-turn safety classification—frequently fail when confronted with subtle regional...
