DataPraxis：通过已验证工作区演化扩展分析任务
原标题：DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution
AI 摘要
该论文提出 DataPraxis，一个基于「已验证工作区演化」的分析任务合成框架：通过逐步积累经校验的分析发现与产物，并继承、组合工作区来挖掘更深层问题，再用双重证据校验构建评估标准。作者据此构建了覆盖 15 个领域的 5,000 条已验证轨迹数据集 DataPraxis-5K，并训练出 DataPraxis-27B 与 DataPraxis-35B-A3B；其中 DataPraxis-27B 在 DABStep 上得 55.11、JobBench 上得 51.9，追平或超过 GLM-5.2 等前沿模型。
正文节选
DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution Abstract General-purpose agents are increasingly expected to perform professional analytics work, which requires sustained reasoning, iterative investigation, and reliable evidence. Training these capabilities requires diverse and challenging tasks. However, generating tasks directly from raw data often overlooks deeper questions that emerge through analysis and provides limited evidence for verification. To address these limi