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.

We introduce IQuest-Coder-V1, a high-performance code LLM that achieves leading results on multiple public benchmarks, surpassing several competitive closed-source models. I mainly contributed to the post-training design and optimization, with a particular emphasis on Text-to-SQL reasoning and terminal-level execution tasks, substantially improving the model’s practical reasoning and action fidelity, surpassing the cutting-edge LLMs.

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.