IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems

One-line takeaway

IQuest-Q1 is a sparse MoE agentic foundation model for CLI agents (320B total, 15B active), trained in three stages: stable pre-training (Stable SplitNorm, Muon, muP) with a code-heavier second curriculum stage, mid-training with broader data and longer context, and multi-scaffold post-training combining SFT, domain RL and MOPD.

IQuest-Q1 是面向命令行智能体的稀疏 MoE 基座模型，总参数 320B、激活 15B；三阶段训练：用 Stable SplitNorm、Muon、muP 稳定预训练并在第二阶段加大代码数据，中训扩展数据与上下文长度，后训练在多种脚手架上结合 SFT、领域 RL 和 MOPD。