Skip to content
conftrace_
2026 EMNLP EMNLP 2026

DSFlow: Evolutionary Workflow Optimization for Generalizable LLM-Based Data Science Automation

AbstractLarge language model (LLM) agents create new opportunities for end-to-end data science automation, but existing systems often overfit to dataset-specific schemas, preprocessing routines, and code patterns, making them brittle under task shifts and costly to reuse. We propose DSFlow, a workflow-optimization framework that represents data-science solutions as compositions of reusable operators rather than monolithic, dataset-coupled programs. DSFlow evolves operator-based workflows to discover transferable structures, expands its operator library through synthesis and composition, and uses a two-stage evaluation strategy that filters candidates with inexpensive plan-level scoring before selectively running full executions. This design keeps optimization practical while improving transfer to unseen tasks. Experiments on heterogeneous benchmarks spanning tabular, image, text, and time-series modalities show that DSFlow achieves strong zero-shot generalization, reaching an average rank of 2.62. In addition, DSFlow grows its operator library from 10 manually designed operators to more than 70 discovered ones, improving accuracy from 0.8070 to 0.8448 and demonstrating scalable knowledge accumulation.

More from EMNLP 2026

All EMNLP 2026 papers →