# OraPlan-SQL: A Planning-Centric Framework for Complex Bilingual NL2SQL Reasoning

arXiv: https://arxiv.org/abs/2510.23870 · HTML: https://mlsanity.com/paper/2510.23870/

## Key facts

- Cited by 3 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 7 of its 12 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 7 of 7)

- [CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL](https://mlsanity.com/paper/2410.01943/) (2024)
- [Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect](https://mlsanity.com/paper/2208.10099/) (2022)
- [AgenticData: An Agentic Data Analytics System for Heterogeneous Data](https://mlsanity.com/paper/2508.05002/) (2025)
- [Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge](https://mlsanity.com/paper/2301.01067/) (2023)
- [Archer: A Human-Labeled Text-to-SQL Dataset with Arithmetic, Commonsense and Hypothetical Reasoning](https://mlsanity.com/paper/2402.12554/) (2024)
- [LogicCat: A Chain-of-Thought Text-to-SQL Benchmark for Complex Reasoning](https://mlsanity.com/paper/2505.18744/) (2025)
- [RAISE: Reasoning Agent for Interactive SQL Exploration](https://mlsanity.com/paper/2506.01273/) (2025)

## Built on by (most cited first, 3 of 3)

- [Agentics 2.0: Logical Transduction Algebra for Agentic Data Workflows](https://mlsanity.com/paper/2603.04241/) (2026)
- [SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probing](https://mlsanity.com/paper/2606.11424/) (2026)
- [PLSQLBench: Benchmarking LLM Systems for Executable Procedural Database Programming](https://mlsanity.com/paper/2608.15931/) (2026)

## Abstract (arXiv)

We present OraPlan-SQL, our system for the Archer NL2SQL Evaluation Challenge 2025, a bilingual benchmark requiring complex reasoning such as arithmetic, commonsense, and hypothetical inference. OraPlan-SQL ranked first, exceeding the second-best system by more than 6% in execution accuracy (EX), with 55.0% in English and 56.7% in Chinese, while maintaining over 99% SQL validity (VA). Our system follows an agentic framework with two components: Planner agent that generates stepwise natural language plans, and SQL agent that converts these plans into executable SQL. Since SQL agent reliably adheres to the plan, our refinements focus on the planner. Unlike prior methods that rely on multiple sub-agents for planning and suffer from orchestration overhead, we introduce a feedback-guided meta-prompting strategy to refine a single planner. Failure cases from a held-out set are clustered with human input, and an LLM distills them into corrective guidelines that are integrated into the planner's system prompt, improving generalization without added complexity. For the multilingual scenario, to address transliteration and entity mismatch issues, we incorporate entity-linking guidelines that generate alternative surface forms for entities and explicitly include them in the plan. Finally, we enhance reliability through plan diversification: multiple candidate plans are generated for each query, with the SQL agent producing a query for each plan, and final output selected via majority voting over their executions.