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

• URL: http://arxiv.org/abs/2510.10885v1
• Date: Mon, 13 Oct 2025 01:29:54 GMT
• Title: Rethinking Agentic Workflows: Evaluating Inference-Based Test-Time Scaling Strategies in Text2SQL Tasks
• Abstract summary: Large language models (LLMs) are increasingly powering Text-to- (Text2) systems, enabling non-expert users to query industrial databases using natural language.<n>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.<n>This work sheds light on the practical trade-offs between accuracy, efficiency, and complexity when deploying Text2 systems.
• Score: 21.891522433628893
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• SQuaD-SQL: Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillation [10.706234312157278]
  Small language models (SLMs) can approach the performance of large language models (LLMs) on the Text-to-Small task while significantly improving efficiency through knowledge distillation and synthetic data generation.<n>Experiments on the Wiki dataset demonstrate that SQuaD-Small achieves an execution accuracy of 86.9% on the test set while offering faster inference and lower memory usage.
  arXiv  Detail & Related papers  (2026-07-09T06:56:20Z)
• OpenCompass: A Universal Evaluation Platform for Large Language Models [62.59671563145442]
  General-purpose large language models (LLMs) have become a critical link in advancing technological development.<n>Mainstream benchmark datasets face challenges such as the diversity of task types, inconsistent evaluation criteria, and fragmentation of data and processing.<n>This paper proposes and open-source Open LLMs, a one-stop, scalable, and high-concurrency general-purpose evaluation platform.
  arXiv  Detail & Related papers  (2026-05-19T02:50:11Z)
• NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions [16.53346245559808]
  Large language models (LLMs) have greatly improved NL2 algorithms, but their rapid development outpaces systematic evaluation.<n>We present NL2Bench, the first modular evaluation and benchmarking framework for unified-enabled NL2 approaches.<n>Our evaluation reveals significant gaps in existing NL2 methods, highlighting not only substantial room for accuracy improvements but also the significant computational inefficiency.
  arXiv  Detail & Related papers  (2026-04-13T18:00:05Z)
• Beyond Naïve Prompting: Strategies for Improved Zero-shot Context-aided Forecasting with LLMs [57.82819770709032]
  Large language models (LLMs) can be effective context-aided forecasters via na"ive direct prompting.<n>ReDP improves interpretability by eliciting explicit reasoning traces, allowing us to assess the model's reasoning over the context.<n>CorDP leverages LLMs solely to refine existing forecasts with context, enhancing their applicability in real-world forecasting pipelines.<n> IC-DP proposes embedding historical examples of context-aided forecasting tasks in the prompt, substantially improving accuracy even for the largest models.
  arXiv  Detail & Related papers  (2025-08-13T16:02:55Z)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• MCTS-SQL: Light-Weight LLMs can Master the Text-to-SQL through Monte Carlo Tree Search [1.166711394125328]
  Text-to-OTA is a fundamental yet challenging task in the NLP area.<n>We propose MCTS-OTA, a novel framework that uses Monte Carlo Tree Search.<n>We propose a token-level prefixcache mechanism that stores prior information during iterations.
  arXiv  Detail & Related papers  (2025-01-28T00:52:23Z)
• Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL [83.99974309930072]
  Knowledge distillation (KD) is a common approach, which aims to distill the larger teacher model into a smaller student model. We propose to improve the KD with Imperfect Data, namely KID, which effectively boosts the performance without introducing much training budget. KID can not only achieve consistent and significant performance gains across all model types and sizes, but also effectively improve the training efficiency.
  arXiv  Detail & Related papers  (2024-10-15T07:51:00Z)
• Interactive-T2S: Multi-Turn Interactions for Text-to-SQL with Large Language Models [9.914489049993495]
  We introduce Interactive-T2S, a framework that generatessql queries through direct interactions with databases. We have developed detailed exemplars to demonstrate the step-wise reasoning processes within our framework. Our experiments on the BIRD-Dev dataset, employing a setting without oracle knowledge, reveal that our method achieves state-of-the-art results with only two exemplars.
  arXiv  Detail & Related papers  (2024-08-09T07:43:21Z)
• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? [54.667202878390526]
  Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. We introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning. Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks.
  arXiv  Detail & Related papers  (2024-06-19T00:28:58Z)
• Benchmarking the Text-to-SQL Capability of Large Language Models: A Comprehensive Evaluation [33.41556606816004]
  Large Language Models (LLMs) have emerged as a powerful tool in advancing the Text-to- task. There is still no consensus on the optimal prompt templates and design frameworks. Existing benchmarks inadequately explore the performance of LLMs across the various sub-tasks of the Text-to- process.
  arXiv  Detail & Related papers  (2024-03-05T13:23:48Z)
• Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation [76.76046657162306]
  Large language models (LLMs) have emerged as a new paradigm for Text-to- task. Large language models (LLMs) have emerged as a new paradigm for Text-to- task.
  arXiv  Detail & Related papers  (2023-08-29T14:59:54Z)
• SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended) [53.95151604061761]
  This paper introduces the framework for enhancing Text-to- filtering using large language models (LLMs) With few-shot prompting, we explore the effectiveness of consistency decoding with execution-based error analyses. With instruction fine-tuning, we delve deep in understanding the critical paradigms that influence the performance of tuned LLMs.
  arXiv  Detail & Related papers  (2023-05-26T21:39:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.