# Generating Workflow DAGs from Natural Language with Non-Reasoning LLMs

arXiv: https://arxiv.org/abs/2608.30250 · HTML: https://mlsanity.com/paper/2608.30250/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 16 of its 16 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 16 of 16)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [Self-Preference Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2410.21819/) (2024)
- [Efficient Guided Generation for Large Language Models](https://mlsanity.com/paper/2307.09702/) (2023)
- [Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning](https://mlsanity.com/paper/2305.13971/) (2023)
- [Flexible and Efficient Grammar-Constrained Decoding](https://mlsanity.com/paper/2502.05111/) (2025)
- [Benchmarking Agentic Workflow Generation](https://mlsanity.com/paper/2410.07869/) (2024)
- [FlowMind: Automatic Workflow Generation with LLMs](https://mlsanity.com/paper/2404.13050/) (2024)
- [WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models](https://mlsanity.com/paper/2411.05451/) (2024)
- [RobustFlow: Towards Robust Agentic Workflow Generation](https://mlsanity.com/paper/2509.21834/) (2025)
- [NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional Generalization](https://mlsanity.com/paper/2412.15588/) (2024)
- [Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation](https://mlsanity.com/paper/2604.05150/) (2026)
- [On LLM-Assisted Generation of Smart Contracts from Business Processes](https://mlsanity.com/paper/2507.23087/) (2025)
- [RaTA-Tool: Retrieval-based Tool Selection with Multimodal Large Language Models](https://mlsanity.com/paper/2604.14951/) (2026)

## Abstract (arXiv)

This paper addresses the problem of translating natural-language routing rules written by business administrators into executable workflow graphs for enterprise contact centers. Each target is a directed acyclic graph (DAG) of conditional actions with parallel branches, hit-first fallback chains, and per-branch Boolean predicates, encoded in the JSON dialect of a commercial routing platform. We show that neuro-symbolic decomposition enables lower-cost, non-reasoning large language models to generate complex workflow DAGs at production-relevant quality without expensive extended-reasoning models. Our central diagnostic is an emission-density bottleneck: on a 635-rule benchmark of manufactured synthetic data, models select the correct graph nodes with high accuracy but increasingly misconfigure attributes and Boolean grouping as the number of interdependent nodes emitted in one pass grows. We therefore move combinatorial graph construction from the model into a deterministic compiler driven by a compact intermediate representation, with a learned registry-selection front end that focuses generation on relevant vocabulary. Across four models, the full system reaches approximately 89% LLM-judge validity, approximately 90% exact-match condition accuracy, and 99-100% valid JSON while using roughly half the per-rule prompt tokens of a monolithic prompt. On GPT-5.3-chat, the method improves judge validity by 24 percentage points and achieves statistical equivalence to a reasoning model's out-of-the-box quality, although an approximately 8-point frontier gap remains. We also present a deployment path and transferable lessons for structured-generation applications.