FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents

• URL: http://arxiv.org/abs/2605.02815v1
• Date: Mon, 04 May 2026 16:51:31 GMT
• Title: FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents
• Abstract summary: We present Flex Code, a text-to-agent whose core design principle is flexible database interaction.<n>Our approach yields over 10% relative improvement on Spider2-Snow.
• Score: 36.84900072417659
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-SQL over large analytical databases requires navigating complex schemas, resolving ambiguous queries, and grounding decisions in actual data. Most current systems follow a fixed pipeline where schema elements are retrieved once upfront and the database is only revisited for post-hoc repair, limiting recovery from early mistakes. We present FlexSQL, a text-to-SQL agent whose core design principle is flexible database interaction: the agent can explore schema structure, inspect data values, and run verification queries at any point during reasoning. FlexSQL generates diverse execution plans to cover multiple query interpretations, implements each plan in either SQL or Python depending on the task, and uses a two-tiered repair mechanism that can backtrack from code-level errors to plan-level revisions. On Spider2-Snow, using gpt-oss-120b, FlexSQL achieves a 65.4\% score, outperforming strong open-source baselines that use stronger, larger models such as gpt-o3 and DeepSeek-R1. When integrated into a general-purpose coding agent (as skills in Claude Code), our approach yields over 10\% relative improvement on Spider2-Snow. Further analysis shows that flexible exploration and flexible execution jointly contribute to the effectiveness of our approach, highlighting flexibility as a key design principle. Our code is available at: https://github.com/StringNLPLAB/FlexSQL

Related papers

• Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows [54.49251107006261]
  We introduce Spider 2.0-AIFunc, a benchmark of 465 verified instances across 125 real-world databases covering six types of AI functions on the Snowflake platform.<n>We find that the strongest proprietary models reach 67-70% execution accuracy while the best open-source model achieves 58.1%.
  arXiv  Detail & Related papers  (2026-07-07T12:54:08Z)
• ProSPy: A Profiling-Driven SQL-Python Agentic Framework for Enterprise Text-to-SQL [51.98164069124653]
  ProSPy is a Profiling-driven framework for enterprise-scale Text-to-gnostic analysis.<n>ProSPy structures the reasoning process into four stages.<n>It first extracts fine-grained data evidence through automatic profiling.<n>It prunes large schemas into task-relevant contexts.
  arXiv  Detail & Related papers  (2026-06-04T08:13:05Z)
• Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration [21.94739453628141]
  We introduce Dy-Bench, a benchmark assessing model performance under evolving user interactions.<n>Unlike previous manually curated datasets, Dylz-Bench is built through an automated two-stage pipeline of task and verification.<n>Dy-Bench covers 13 domains across BIRD and Spider 2 databases, totaling 1,072 tasks.
  arXiv  Detail & Related papers  (2025-10-30T13:44:22Z)
• From Queries to Insights: Agentic LLM Pipelines for Spatio-Temporal Text-to-SQL [8.496933324334167]
  We present a naive text-to-Act baseline (Rellama-sqlcoder-8b) with orchestration by a Mistral-based Rellama-sqlcoder-8b.<n>We evaluate on 35 natural-language queries over the NYC and Tokyo check-in, covering spatial, temporal multi-dataset reasoning.<n>The agent achieves substantially higher accuracy than the dataset 91.4% vs. 28.6% and enhances usability through maps, and plots structured natural-language summaries.
  arXiv  Detail & Related papers  (2025-10-29T22:18:57Z)
• X-SQL: Expert Schema Linking and Understanding of Text-to-SQL with Multi-LLMs [0.0]
  We find that database schema information plays a significant or even dominant role in the Text-to-Admin task.<n>We introduce X-Supervised Finetuning (SFT) that achieves superior Linking results compared to existing open-source Text-to-Admin methods.<n>In addition, we propose an X- component that focuses on Understanding by bridging the gap between abstract information and the user's natural language question.
  arXiv  Detail & Related papers  (2025-09-07T02:51:43Z)
• ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration [32.83579488224367]
  We present ReFoRCE, a Text-to-confidence agent that tops the Spider 2.0 leaderboard.<n>ReFoRCE achieves state-of-the-art results, with scores of 35.83 Spider 2.0-Snow and 36.56 on Spider 2.0-Lite.
  arXiv  Detail & Related papers  (2025-02-02T05:25:03Z)
• Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows [64.94146689665628]
  Spider 2.0 is an evaluation framework for real-world text-to-sql problems derived from enterprise-level database use cases.<n>The databases in Spider 2.0 are sourced from real data applications, often containing over 1,000 columns and stored in local or cloud database systems such as BigQuery and Snowflake.<n>We show that solving problems in Spider 2.0 frequently requires understanding and searching through database metadata, dialect documentation, and even project-levels.
  arXiv  Detail & Related papers  (2024-11-12T12:52:17Z)
• MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL [47.120862170230566]
  Recent Text-to-yourself methods usually suffer from significant performance degradation on "huge" databases.<n>We introduce MAC, a novel Text-to-yourself LLM-based multi-agent collaborative framework.<n>In our framework, we leverage GPT-4 as the strong backbone for all agent tasks to determine the upper bound of our framework.<n>We then fine-tune an open-sourced instruction-followed model,sql-Llama, by leveraging Code 7B, to accomplish all tasks as GPT-4 does.
  arXiv  Detail & Related papers  (2023-12-18T14:40:20Z)
• 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)
• UNITE: A Unified Benchmark for Text-to-SQL Evaluation [72.72040379293718]
  We introduce a UNIfied benchmark for Text-to-domain systems. It is composed of publicly available text-to-domain datasets and 29K databases. Compared to the widely used Spider benchmark, we introduce a threefold increase in SQL patterns.
  arXiv  Detail & Related papers  (2023-05-25T17:19:52Z)

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.