# Classifier-Augmented Generation for Structured Workflow Prediction

arXiv: https://arxiv.org/abs/2510.12825 · HTML: https://mlsanity.com/paper/2510.12825/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 40 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 8 of 8)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [AutoFlow: Automated Workflow Generation for Large Language Model Agents](https://mlsanity.com/paper/2407.12821/) (2024)
- [FlowMind: Automatic Workflow Generation with LLMs](https://mlsanity.com/paper/2404.13050/) (2024)
- [Scaling Granite Code Models to 128K Context](https://mlsanity.com/paper/2407.13739/) (2024)

## Built on by (most cited first, 1 of 1)

- [FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoning](https://mlsanity.com/paper/2602.11782/) (2026)

## Abstract (arXiv)

ETL (Extract, Transform, Load) tools such as IBM DataStage allow users to visually assemble complex data workflows, but configuring stages and their properties remains time consuming and requires deep tool knowledge. We propose a system that translates natural language descriptions into executable workflows, automatically predicting both the structure and detailed configuration of the flow. At its core lies a Classifier-Augmented Generation (CAG) approach that combines utterance decomposition with a classifier and stage-specific few-shot prompting to produce accurate stage predictions. These stages are then connected into non-linear workflows using edge prediction, and stage properties are inferred from sub-utterance context. We compare CAG against strong single-prompt and agentic baselines, showing improved accuracy and efficiency, while substantially reducing token usage. Our architecture is modular, interpretable, and capable of end-to-end workflow generation, including robust validation steps. To our knowledge, this is the first system with a detailed evaluation across stage prediction, edge layout, and property generation for natural-language-driven ETL authoring.