Reproduce “IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
A. Jian Yang, An Huang, Bo Dan, Chen Mu, Chengran Yang, Chuan Shi, Feng Chang, Hongxin Li and 169 more
IQuest-Q1 is an open-weight model designed for command-line agents that reason, use tools, and act in external systems. Its 320B parameters, with 15B activated per token, are trained in stages, then specialized in executable environments and combined across agent skills. On Terminal-Bench 2.1, it scores 83.2, below GLM-5.3-Flash and Claude Opus 5, demonstrating capability but not leadership.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.