# Rethinking Agentic Workflows: Evaluating Inference-Based Test-Time Scaling Strategies in Text2SQL Tasks

arXiv: https://arxiv.org/abs/2510.10885 · HTML: https://mlsanity.com/paper/2510.10885/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 2 of its 9 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 2 of 2)

- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)

## Built on by (most cited first, 2 of 2)

- [CompAgent: An Agentic Framework for Visual Compliance Verification](https://mlsanity.com/paper/2511.00171/) (2025)
- [ACTS-SQL: Agentic and Critic-Oriented Tree-Structured SQL Correctness with Large Language Models](https://mlsanity.com/paper/2608.15145/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly powering Text-to-SQL (Text2SQL) systems, enabling non-expert users to query industrial databases using natural language. While test-time scaling strategies have shown promise in LLM-based solutions, their effectiveness in real-world applications, especially with the latest reasoning models, remains uncertain. In this work, we benchmark six lightweight, industry-oriented test-time scaling strategies and four LLMs, including two reasoning models, evaluating their performance on the BIRD Mini-Dev benchmark. Beyond standard accuracy metrics, we also report inference latency and token consumption, providing insights relevant for practical system deployment. Our findings reveal that Divide-and-Conquer prompting and few-shot demonstrations consistently enhance performance for both general-purpose and reasoning-focused LLMs. However, introducing additional workflow steps yields mixed results, and base model selection plays a critical role. This work sheds light on the practical trade-offs between accuracy, efficiency, and complexity when deploying Text2SQL systems.