IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems | Code

IQuest-Q1 is an open-source agentic foundation model for CLI systems. A sparse Mixture-of-Experts model with 320B total parameters and 15B activated, it combines general and coding agent capabilities with efficient compute for medium- and long-horizon tasks. During development, it also takes part in its own improvement under human supervision.

Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments | Code

Siwei Wu*, Yizhi Li*, Yuyang Song*, Wei Zhang, Riza Batista-Navarro, Xian yang, Mingjie Tang, Bryan Dai, Jian Yang, Chenghua Lin.

We study how large-scale, execution-grounded terminal trajectories reshape the agentic capabilities of code LLMs. Trained on this data, TerminalTraj-32B achieves state-of-the-art results among models under 100B parameters and matches models more than 10× larger, while showing markedly steeper test-time scaling—evidence that the right training data, not just scale, drives terminal agent capability.

IQuest-Coder-V1 Technical Report | Code

Jian Yang, Wei Zhang, Shawn Guo, Zhengmao Ye, Lin Jing, Shark Liu, Yizhi Li, Jiajun Wu, Cening Liu, X. Ma, Yuyang Song, et al.

IQuest-Coder-V1 is a Looped-Transformer-based code large language models (LLMs) designed to advance autonomous software engineering and code intelligence. Built on the innovative code-flow multi-stage training paradigm, IQuest-Coder-V1 captures the dynamic evolution of software logic, delivering state-of-the-art performance across critical dimensions.

QUITE: A Query Rewrite System Beyond Rules with LLM Agents | Code

Yuyang Song, Hanxu Yan, Jiale Lao, Yibo Wang, Yufei Li, Yuanchun Zhou, Jianguo Wang, Mingjie Tang

QUITE is a training-free and feedback-aware system based on LLM agents that rewrites SQL queries into semantically equivalent forms with significantly better performance, covering a broader range of query patterns and rewrite strategies compared to rule-based methods.