This work constructs DataPraxis-5K, a dataset of 5,000 verified trajectories spanning diverse domains and output formats, to train DataPraxis-27B and DataPraxis-35B-A3B, an analytics task synthesis framework based on verified workspace evolution.
Nan Jia, Wen-Xuan Shi, Jing-Qing Ruan et al.· 0 citations
DivOPD, a simple learner-side batch-selection method that spreads a fixed turn budget across more rollouts and, within each rollout, prioritizes turns with larger cumulative teacher-student disagreement, is introduced.
Han-Yang Wang, Ze-Yuan Liu, Zheng-Yu Chen et al.· 0 citations
Remarkably, despite operating entirely without pre-loaded metadata, the proposed TRUST-SQL framework consistently matches or surpasses strong baselines that rely on schema prefilling.
Ai Jian, Xiao-Yun Zhang, Er-Yu Guo et al.· arXiv.org· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.