arXiv：cs.CL· SAIL Model Team, Boyuan Sun, Bryan Dai, Che Liu, Chi Liu, Derek Li, Hongming Piao, Mengzhuo Chen, Xidong Wang, Yan Shu, Yinda Chen, Ziyang Zeng·· 3 小时前
SAIL：通过科学感知循环打造的科学智能体模型
SAIL: Scientific Agentic Intelligence via a Science-Aware Loop
AI 导读
SAIL 是一个总参数 35B、激活参数 3B 的开放模型，面向文献研究、科学编程和多步科研工作流。
正文
Authors:SAIL Model Team: Boyuan Sun, Bryan Dai, Che Liu, Chi Liu, Derek Li, Hongming Piao, Mengzhuo Chen, Xidong Wang, Yan Shu, Yinda Chen, Ziyang Zeng
Abstract:We introduce SAIL, an open model with 35B total and 3B active parameters for literature research, scientific coding, and multi-step research workflows. SAIL is developed through a science-aware improvement loop: agents built on frontier AI models analyze its task failures and construct training tasks that address the underlying capability gaps. The diagnosis examines search and evidence selection in literature tasks, scientific assumptions and reasoning in coding, and planning and revision in longer investigations. The agents draw on paper collections and scientific code repositories to build problems, interaction trajectories, and executable tasks with the required environments and tools. We repeat this loop over multiple development cycles and train SAIL through supervised fine-tuning, specialist training, multi-teacher on-policy distillation, and agentic reinforcement learning. SAIL achieves competitive performance across scientific research tasks with substantially fewer parameters than leading open-weight models.
| Comments: | 16 pages, technical report |
| Subjects: | Computation and Language (cs.CL); Digital Libraries (cs.DL); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2610.11451 [cs.CL] |
| (or arXiv:2610.11451v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11451 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Chi Liu [view email]
[v1]
Thu, 8 Oct 2026 08:04:22 UTC (2,179 KB)
来源：arXiv：cs.CL · arxiv.org