PExA: Parallel Exploration Agent for Complex Text-to-SQL
On the map: LLM agents and tool use → Web, search, and research agents
Abstract (arXiv)
LLM-based agents for text-to-SQL often struggle with latency-performance trade-off, where performance improvements come at the cost of latency or vice versa. We reformulate text-to-SQL generation within the lens of software test coverage where the original query is prepared with a suite of test cases with simpler, atomic SQLs that are executed in parallel and together ensure semantic coverage of the original query. After iterating on test case coverage, the final SQL is generated only when enough information is gathered, leveraging the explored test case SQLs to ground the final generation. We validated our framework on a state-of-the-art benchmark for text-to-SQL, Spider 2.0, achieving a new state-of-the-art with 70.2% execution accuracy.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 43 of its 67 references that are in the map. First posted on arXiv 24 Apr 2026.
Builds on
43 of 67 references.
Closest ancestors · 3
Same direction, newest first
- 2025AgenticData: An Agentic Data Analytics System for Heterogeneous Data7 Aug
- 2024MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQL15 Aug
- 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL18 Dec
Other references · 40
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
- 2023Let's Verify Step by Stepcited by 3,598
- 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
- 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
- 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
- 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
- 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
- 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
- 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
- 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
- 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
28 more
- 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
- 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
- 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 183
- 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
- 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
- 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
- 2020Structure-Grounded Pretraining for Text-to-SQLcited by 126
- 2023A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capabilitycited by 118
- 2023Branch-Solve-Merge Improves Large Language Model Evaluation and Generationcited by 104
- 2024MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generationcited by 103
- 2021Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalizationcited by 92
- 2019Text-to-SQL Generation for Question Answering on Electronic Medical Recordscited by 76
- 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQLcited by 38
- 2025SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositoriescited by 27
- 2025Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selectioncited by 23
- 2022Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignmentcited by 16
- 2024Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruningcited by 16
- 2025STaR-SQL: Self-Taught Reasoner for Text-to-SQLcited by 16
- 2024Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQLcited by 12
- 2024Improving Demonstration Diversity by Human-Free Fusing for Text-to-SQLcited by 10
- 2024BookSQL: A Large Scale Text-to-SQL Dataset for Accounting Domaincited by 10
- 2022T5QL: Taming language models for SQL generationcited by 8
- 2024SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparednesscited by 6
- 2025Decompose, Plan in Parallel, and Merge: A Novel Paradigm for Large Language Models based Planning with Multiple Constraintscited by 5
- 2025BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge Basescited by 4
- 2025SNaRe: Domain-aware Data Generation for Low-Resource Event Detectioncited by 2
- 2025DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoningcited by 2
- 2024Iterative Repair with Weak Verifiers for Few-shot Transfer in KBQA with Unanswerabilitycited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025BAPPA: Benchmarking Agents, Plans, and Pipelines for Automated Text-to-SQL Generation
- 2025Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling
- 2026APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL
- 2026AgentSM: Semantic Memory for Agentic Text-to-SQL
- 2026FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents
- 2025ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration
- 2025AGENTIQL: An Agent-Inspired Multi-Expert Framework for Text-to-SQL Generation
- 2026Iteration Without Elaboration: A Simple ReAct Architecture Suffices for Text-to-SQL Generation