发表机构
IQuest Research（智趣研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究人员开发了总参数35B、激活参数3B的开放模型SAIL，通过科学感知改进循环训练，在科学研究任务中性能具竞争力，参数远少于领先开放权重模型。
AI 中文摘要
我们推出SAIL，这是一款总参数为35B、激活参数为3B的开放模型，用于文献研究、科学编码及多步骤研究工作流。SAIL通过科学感知改进循环开发：基于前沿AI模型构建的智能体分析其任务失败情况，并构建训练任务以解决潜在的能力缺口。诊断环节涵盖文献任务中的搜索与证据选择、编码中的科学假设与推理，以及较长研究中的规划与修订。这些智能体利用论文集和科学代码库构建问题、交互轨迹及具备所需环境与工具的可执行任务。我们在多个开发周期中重复此循环，并通过监督微调、专家训练、多教师在线策略蒸馏及智能体强化学习对SAIL进行训练。SAIL在科学研究任务中取得了具有竞争力的性能，且参数数量远少于领先的开放权重模型。
英文摘要
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.
Comments16 pages, technical report
