DSFlow: A Neuro-Symbolic Data Workflow Agent with Statistical Diagnostic Guardrails
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
| System | Regression | Clustering | Criteria met |
|---|---|---|---|
| DSFlow | 42/42 | ||
| Manus | 19/42 | ||
| Gemini | 10/42 | ||
| ChatGPT | 8/42 |
| Policy | R-A | R-O | C-A | C-O | Total |
|---|---|---|---|---|---|
| Selective router | 18/20 | 19/20 | 20/20 | 20/20 | 77/80 |
| No override | 20/20 | 0/20 | 20/20 | 0/20 | 40/80 |
| Constant default | 20/20 | 0/20 | 20/20 | 0/20 | 40/80 |
| Constant complex | 0/20 | 20/20 | 0/20 | 20/20 | 40/80 |
| Model | Task | Target | Features | Plan | Clar. R | Fails |
|---|---|---|---|---|---|---|
| Llama 3.3 70B | 24/25 | 12/12 | 22/22 | 21/21 | 4/4 | 0 |
| Llama 3.1 8B | 24/25 | 12/12 | 22/22 | 21/21 | 4/4 | 0 |
| Condition | Generator | Rows | Preference | Expected method |
|---|---|---|---|---|
| R- Accept | Linear Gaussian | 1,000 | OLS | OLS |
| R- Override | Paired contaminated linear | 1,000 | OLS | Huber regression |
| C- Accept | Gaussian blobs | 900 | -means | -means |
| C- Override | Disc and two rings | 1,000 | -means | Spectral clustering |
| Multiplier | Correct | R- Accept | R- Override | Median RMSE |
|---|---|---|---|---|
| 0.50 | 20/40 | 0/20 | 20/20 | 1.013 |
| 0.75 | 20/40 | 0/20 | 20/20 | 1.013 |
| 1.00 | 37/40 | 18/20 | 19/20 | 1.013 |
| 1.25 | 38/40 | 19/20 | 19/20 | 1.013 |
| 1.50 | 38/40 | 19/20 | 19/20 | 1.013 |
| 2.00 | 38/40 | 19/20 | 19/20 | 1.013 |
| Agreement cutoff | Correct | C- Accept | C- Override |
|---|---|---|---|
| 0.50 | 40/40 | 20/20 | 20/20 |
| 0.75 | 40/40 | 20/20 | 20/20 |
| 0.90 | 40/40 | 20/20 | 20/20 |
| 0.95 | 40/40 | 20/20 | 20/20 |
| 0.975 | 40/40 | 20/20 | 20/20 |
| 0.99 | 40/40 | 20/20 | 20/20 |
| Configuration | Regression | Clustering |
|---|---|---|
| Full deterministic core | Robust; RMSE 100,131 | Spectral; sizes 250/250/500 |
| Oracle plan | Same as full core | Same as full core |
| Constant complex | Same as full core | Same as full core |
| Override disabled | OLS; RMSE 127,139 | -means; six sectors |
| Execution guardrail off | Same as full core | Same as full core |
| LLM only | Failed before execution | -means; six groups |
| Rubric criterion | Agreement | Cohen’s |
|---|---|---|
| Regression: detects influence | ||
| Regression: identifies injected rows | ||
| Regression: handles contamination | ||
| Regression: predictive validation | ||
| Regression: quantifies associations | ||
| Regression: interprets limits |
Data Analysis Agents
Data analysis agents use language models and tools to explore datasets, run analyses, and produce answers or reports grounded in evidence.
See all 124 papers