The authors 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, the team applies 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.
- Practical techniques improve rollout and training stability, including partial rollout with off-policy correction, adaptive length regularization, online speculative decoding, robust multi-task optimization, and trace-aware experience assembly.
- Intern-S2-Preview-397B extends time series modelling from efficient long-sequence understanding to numerical forecasting.
- A separate Memory Decoder extension improves the Biology-Instructions average score from 56.92 to 60.32 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.