cs.AINov 18, 2026

DSFlow: A Neuro-Symbolic Data Workflow Agent with Statistical Diagnostic Guardrails

Authors: Junfeng Nie, Xiaohui Chen

Organizations: AnyFluxion · University of Southern California

Abstract

Data science workflows often require tools that presume non-trivial technical knowledge. Large language models (LLMs) reduce this barrier, but a gap remains between flexible general-purpose agents and statistically controlled pipelines. We introduce DSFlow, a LangGraph-based neuro-symbolic data-agent platform that combines reusable, LLM-selected skills with deterministic diagnostic guardrails. Skills provide extensible task knowledge. Symbolic validation can accept a proposed method, request clarification or replanning, override an unsuitable method, or supply a safe fallback. Regression and clustering case studies illustrate how DSFlow uses diagnostic evidence to correct method choices and documents those decisions in auditable reports.

Figures & tables

Explore similar work

CardsList
  1. BobFlow: Towards Human-Agent Collaborative Data Science Using Dataflows

    Nov 4, 2026Jiadong Bai, Yicong Huang, Chen LiHuman-AI CollaborationData Analysis Agents

  2. DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines

    Jul 18, 2026Runming He, Zhen Hao Wong, Hao Liang +4LLM GroundingCode Generation

  3. AutoMind: Adaptive Knowledgeable Agent for Automated Data Science

    Jun 12, 2025Yujie Luo, Yixin Ou, Jingsheng Zheng +9Data Analysis AgentsLLM Agents