arXiv 2610.30949 · cs.CL · 2026-10-22
IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
A. Jian Yang, An Huang, Bo Dan, Chen Mu, Chengran Yang, Chuan Shi, Feng Chang, Hongxin Li 等 177 人
IQuest
在最新榜 #273 本站收录于 2026-10-24
一句话要点
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。
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.
阅读 arXiv 原文 PDF Hugging Face 讨论
主题与学科
同主题：智能体
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲388
- Player-1: Learning to Play from Synthetic Experience ▲347
同主题：代码与软件工程
- MaLiang-Harness: A Programmable Path to Image and Video Generation 2026-09-28 · ▲367
- OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use 2026-10-15 · ▲325
- HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents 2026-10-16 · ▲294
- AgentSWE: Can Coding Agents Build the Agent You Actually Want? 2026-10-09 · ▲233
- CodeMidas: Scaling Agentic Coding RL Environments from Code Itself 2026-09-18 · ▲138
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。