pith. sign in

arxiv: 2507.18576 · v3 · pith:OKW3KMRInew · submitted 2025-07-24 · 💻 cs.AI · cs.CL· cs.CV

SafeWork-R1: Coevolving Safety and Intelligence under the AI-45^(circ) Law

Shanghai AI Lab: Yicheng Bao , Guanxu Chen , Mingkang Chen , Yunhao Chen , Chiyu Chen , Lingjie Chen , Sirui Chen , Xinquan Chen
show 108 more authors
Jie Cheng Yu Cheng Dengke Deng Yizhuo Ding Dan Ding Xiaoshan Ding Yi Ding Zhichen Dong Lingxiao Du Yuyu Fan Xinshun Feng Yanwei Fu Yuxuan Gao Ruijun Ge Tianle Gu Lujun Gui Jiaxuan Guo Qianxi He Yuenan Hou Xuhao Hu Hong Huang Kaichen Huang Shiyang Huang Yuxian Jiang Shanzhe Lei Jie Li Lijun Li Hao Li Juncheng Li Xiangtian Li Yafu Li Lingyu Li Xueyan Li Haotian Liang Dongrui Liu Qihua Liu Zhixuan Liu Bangwei Liu Huacan Liu Yuexiao Liu Zongkai Liu Chaochao Lu Yudong Lu Xiaoya Lu Zhenghao Lu Qitan Lv Caoyuan Ma Jiachen Ma Xiaoya Ma Zhongtian Ma Lingyu Meng Ziqi Miao Yazhe Niu Yuezhang Peng Yuan Pu Han Qi Chen Qian Xingge Qiao Jingjing Qu Jiashu Qu Wanying Qu Wenwen Qu Xiaoye Qu Qihan Ren Qingnan Ren Qingyu Ren Jing Shao Wenqi Shao Shuai Shao Dongxing Shi Xin Song Xinhao Song Yan Teng Xuan Tong Yingchun Wang Xuhong Wang Shujie Wang Xin Wang Yige Wang Yixu Wang Yuanfu Wang Futing Wang Ruofan Wang Wenjie Wang Yajie Wang Muhao Wei Xiaoyu Wen Fenghua Weng Yuqi Wu Yingtong Xiong Xingcheng Xu Chao Yang Yue Yang Yang Yao Yulei Ye Zhenyun Yin Yi Yu Bo Zhang Qiaosheng Zhang Jinxuan Zhang Yexin Zhang Yinqiang Zheng Hefeng Zhou Zhanhui Zhou Pengyu Zhu Qingzi Zhu Yubo Zhu Bowen Zhou
This is my paper
classification 💻 cs.AI cs.CLcs.CV
keywords safetysafework-r1capabilitiesdevelopframeworkfurthermethodsmodel
0
0 comments X
read the original abstract

We introduce SafeWork-R1, 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. Finally, we further develop SafeWork-R1-InternVL3-78B, SafeWork-R1-DeepSeek-70B, and SafeWork-R1-Qwen2.5VL-7B. All resulting models demonstrate that safety and capability can co-evolve synergistically, highlighting the generalizability of our framework in building robust, reliable, and trustworthy general-purpose AI.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. DAIN: Dynamic Agent-Based Interaction Network for Efficient and Collaborative Multimodal Reasoning

    cs.CL 2026-06 unverdicted novelty 6.0

    DAIN reframes multimodal fusion as dynamic agent collaboration with sparse activation, claiming SOTA results including 2.6% accuracy gain on ADNI across five benchmarks.

  2. Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment

    cs.AI 2026-05 unverdicted novelty 6.0

    PIA achieves lower attack success rates on persona-based jailbreaks via self-play co-evolution of attacks (PLE) and defenses (PICL) that structurally decouples safety from persona context using unilateral KL-divergence.

  3. SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond

    cs.LG 2026-03 conditional novelty 6.0

    SafeSci creates a large objective benchmark and training resource that reveals safety weaknesses in current LLMs for science and demonstrates measurable improvement through targeted fine-tuning.

  4. ProWAFT: A ROMA-LPD Instance for Workload-Aware and Dynamic Fault Tolerance in FPGA-Based CNN Accelerators

    cs.CL 2026-07 unverdicted novelty 5.0

    ProWAFT proposes a workload-aware dynamic fault-tolerance method for FPGA CNN accelerators via selective TMR and partial reconfiguration, reporting lower composite cost than static TMR or reactive approaches on ResNet...

  5. Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration

    cs.AI 2026-04 unverdicted novelty 4.0

    A deep research agent incorporates progressive confidence estimation and calibration to produce trustworthy reports with transparent confidence scores on claims.