Back to Home
arXiv AI··Papers & Tech

DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution

中文摘要

DataPraxis 引入“验证工作区演进”框架,通过迭代推理与证据验证扩展 AI 的专业分析任务,解决了任务生成中的深度和可靠性瓶颈。

English Summary

DataPraxis introduces Verified Workspace Evolution to scale complex analytics tasks for AI agents, enhancing reasoning and verification through iterative, evidence-based investigation of raw data.

Original Excerpt

arXiv:2610.26924v1 Announce Type: new 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 limitations, we introduce DataPraxis, an analytics task synthesis framework based on verified workspace evolution. The framework progressively enriches workspaces with validated findings and artifacts, then inherits and combines these workspaces to uncover deeper questions. It constructs tasks from accumulated findings and their dependencies, verifying analytical results both during evolution and after task assembly. Using this framework, we construct DataPraxis-5K, a dataset of 5,000 verified trajectories spanning diverse domains and output formats, to train DataPraxis-27B and DataPraxis-35B-A3B. DataPraxis-27B achieves 55.11 on DABStep and 51.9 on JobBench, matching or surpassing frontier models such as GLM-5.2. DataPraxis-…