SafeWork-R1: Coevolving Safety and Intelligence under the AI-45° Law
Published in arXiv, 2025
SafeWork-R1 is a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. It is developed by our proposed SafeLadder framework, which incorporates large-scale, progressive, safety-oriented reinforcement learning post-training, supported by a suite of multi-principled verifiers. Unlike previous alignment methods such as RLHF that simply learn human preferences, SafeLadder enables SafeWork-R1 to develop intrinsic safety reasoning and self-reflection abilities, giving rise to safety ‘aha’ moments.
Notably, SafeWork-R1 achieves an average improvement of 46.54% over its base model Qwen2.5-VL-72B on safety-related benchmarks without compromising general capabilities, and delivers state-of-the-art safety performance compared to leading proprietary models such as GPT-4.1 and Claude Opus 4. To further bolster its reliability, we implement two distinct inference-time intervention methods and a deliberative search mechanism, enforcing step-level verification.
Recommended citation: Shanghai AI Lab et al. (2025). "SafeWork-R1: Coevolving Safety and Intelligence under the AI-45° Law." arXiv preprint arXiv:2507.18576.
Download Paper