Intern-S2-Preview：科学智能体基础模型

Intern-S2-Preview: Scientific Agentic Foundation Model

August 13, 2026

作者: Lei Bai, Jiaqi Cao, Chiyu Chen, Guanzhou Chen, Kai Chen, Guangran Cheng, Erfei Cui, Xuanlang Dai, Shengyuan Ding, Shangheng Du, Yanhui Duan, Yue Fan, Youqing Fang, Quan Gan, Yuanyuan Gao, Jiaye Ge, Lixin Gu, Yuzhe Gu, Qipeng Guo, Junjun He, Xin Hong, Ming Hu, Zhouqi Hua, Haian Huang, Junhao Huang, Zixian Huang, Minxi Jin, Lingkai Kong, Alexander Lam, Zehao Li, Zonglin Li, Tianhao Liang, Dahua Lin, Junyao Lin, Tianyang Lin, Zhouhan Lin, Jiangning Liu, Jin Liu, Kuikun Liu, Wenran Liu, Yifei Liu, Yuhong Liu, Yuhong Liu, Zhoumianze Liu, Ziyan Liu, Ziyu Liu, Haijun Lv, Han Lv, Chengqi Lyu, Le Ma, Ningsheng Ma, Zerun Ma, Haoyang Peng, Runyu Peng, Jifei Shan, Zixin Shang, Kou Shi, Xiang Shi, Qisheng Su, Xuerui Su, Hao Sun, Xiao Sun, Yanan Sun, Yu Sun, Huanze Tang, Yinghao Tang, Wenhui Tian, Zhongbo Tian, Bingli Wang, Haomin Wang, Jiarui Wang, Jingzhi Wang, Rui Wang, Xiquan Wang, Yi Wang, Zhecan Wang, Ziyi Wang, Zun Wang, Rubin Wei, Lianyi Wu, Wen Wu, Yue Wu, Yuhan Wu, Zhenyu Wu, Zijian Wu, Shuhao Xing, Jun Xu, Xingle Xu, Xuenan Xu, Xiangchao Yan, Ziang Yan, Bowen Yang, Danni Yang, Lin Yang, Zhiqi Yang, Qian Yao, Haochen Ye, Peng Ye, Jinhui Yin, Jiashuo Yu, Dingbo Yuan, Fei Yuan, Yuhang Zang, Bo Zhang, Chao Zhang, Chen Zhang, Hongjie Zhang, Junming Zhang, Wenlong Zhang, Wenwei Zhang, Yiming Zhang, Zhuo Zhang, Ziyang Zhang, Haiteng Zhao, Penghao Zhao, Yibo Zhao, Zhonghan Zhao, Zhihang Zhong, Bowen Zhou, Peiheng Zhou, Xin Zhou, Xinyu Zhou, Yunhua Zhou, Dongsheng Zhu, Yicheng Zou

cs.AI

摘要

科学发现日益需要能够对异构模态的科学证据进行推理、与科学工具和环境交互、并在长任务周期内持续取得进展的AI系统。我们提出Intern-S2-Preview，一系列旨在支持多模态科学理解、推理、生成和长周期任务的科学智能体基础模型。训练流程首先在渲染后的科学文档、图文交错数据和多样化科学语料上进行科学多模态预训练。从预训练检查点出发，我们应用统一的后期训练流程，包括监督微调、可扩展的多任务强化学习（RL）、黑盒与白盒智能体强化学习，以及同策略蒸馏。该流程得到多项实用技术的支撑，这些技术提升了rollout和训练的稳定性与效率，包括带离策略校正的部分rollout、自适应长度正则化、在线投机解码、稳健的多任务优化，以及面向智能体任务的轨迹感知经验组装。在架构层面，Intern-S2-Preview-397B将时间序列建模从高效的长序列理解扩展到数值预测，同时Memory Decoder作为一种独立的记忆增强路径被研究，用于在不修改冻结的397B主干网络的情况下实现快速科学领域专业化。在科学、多模态、智能体和通用基准测试上的评估表明，Intern-S2-Preview-397B在多种场景下取得了具有竞争力或领先的结果。时间序列模块提升了SciTS上的科学信号理解与预测能力，而独立的Intern-MemDec-4B扩展在无需修改冻结的397B主干网络的情况下，将Biology-Instructions平均得分从56.92提升至60.32。

English

Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific tools and environments, and sustain progress across long task horizons. We present Intern-S2-Preview, a series of scientific agentic foundation models designed to support multimodal scientific understanding, reasoning, generation, and long-horizon tasks. The training pipeline begins with scientific multimodal pre-training over rendered scientific documents, interleaved image-text data, and diverse scientific corpora. Starting from the pretrained checkpoint, we apply a unified post-training pipeline consisting of supervised fine-tuning, scalable multi-task reinforcement learning (RL), black- and white-box agentic RL, and on-policy distillation. This pipeline is supported by practical techniques that improve rollout and training stability and efficiency, including partial rollout with off-policy correction, adaptive length regularization, online speculative decoding, robust multi-task optimization, and trace-aware experience assembly for agentic tasks. At the architecture level, Intern-S2-Preview-397B extends time series modelling from efficient long-sequence understanding to numerical forecasting, while Memory Decoder is studied as a separate memory-augmented path for rapid scientific specialization without modifying the frozen 397B backbone. Evaluations across scientific, multimodal, agentic, and general-purpose benchmarks show that Intern-S2-Preview-397B achieves competitive or leading results in multiple settings. The time series modules improve scientific signal understanding and forecasting on SciTS, while the separate Intern-MemDec-4B extension improves the Biology-Instructions average score from 56.92 to 60.32 without modifying the frozen 397B backbone.