Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL (2026.findings-acl)
Copied to clipboard
Zhewei Yao, Guoheng Sun, Łukasz Borchmann, Zheyu Shen, Minghang Deng, Bohan Zhai, Hao Zhang, Ang Li, Yuxiong He
| Challenge: | Translating natural language questions into SQL is a core challenge in natural language understanding and human-computer interaction. |
| Approach: | They propose a reinforcement learning framework and model family to generate accurate, executable SQL using a lightweight reward signal based solely on execution correctness. |
| Outcome: | The proposed framework outperforms previous versions of 70B-class systems and achieves state-of-the-art execution accuracy across six diverse Text2SQL benchmarks. |
Similar Papers
Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward (2025.findings-emnlp)
Copied to clipboard
Han Weng, Puzhen Wu, Cui Longjie, Yi Zhan, Boyi Liu, Yuanfeng Song, Dun Zeng, Yingxiang Yang, Qianru Zhang, Dong Huang, Xiaoming Yin, Yang Sun, Xing Chen
| Challenge: | Existing methods to enhance performance of large language models (LLMs) on Text-to-SQL tasks rely on execution-based or LLM-based reward models. |
| Approach: | They propose a reward model framework for RL-based Text-to-SQL that employs the GMNScore outcome reward model. |
| Outcome: | The proposed reward model outperforms existing reward models on standard benchmarks including Spider and BIRD. |
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large-scale reinforcement learning (RL) methods have proven effective in enhancing the reasoning abilities of large language models. |
| Approach: | They propose an open-source adaptation of the R1-Zero RL framework for machine translation (MT) their code is available at https://github.com/fzp0424/MT-R1-zero. |
| Outcome: | The proposed framework surpasses towerinstruct-7B-v0.2 on the english-chinese benchmark by 1.26 points. |
Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization (2026.eacl-long)
Copied to clipboard
| Challenge: | Text2Vis systems generate functional code but resulting charts lack semantic alignment and clarity. |
| Approach: | They propose a framework that integrates post-execution feedback with textual accuracy, code validity, and visualization quality. |
| Outcome: | The proposed framework outperforms strong zero-shot and supervised baselines and shows robust generalization to out-of-domain datasets. |
SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL (2026.acl-long)
Copied to clipboard
Harper Hua, Zhen Han, Zhengyuan Shen, Meng-Chieh Lee, Sheng Guan, Qi Zhu, Sullam Jeoung, Yueyan Chen, Yunfei Bai, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala
| Challenge: | Recent large language models (LLMs) have significantly improved Text-to-SQL generation, but a gap remains between AI systems and human experts on challenging benchmarks such as BIRD-Sql. |
| Approach: | They propose a multi-turn reinforcement learning agentic framework for Text-to-SQL that uses execution feedback to iteratively refine its predictions. |
| Outcome: | The proposed framework outperforms proprietary systems on 7B and 14B models by **5% on average, underscoring the effectiveness of interactive, agentic workflows for robust Text-to-SQL generation. |
PARSQL: Enhancing Text-to-SQL through SQL Parsing and Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models have made significant strides in text-to-SQL tasks, but small language models struggle to accurately interpret natural language questions due to resource limitations. |
| Approach: | They propose a SQL parser that extracts constraints from SQL to generate sub-SQLs . they use a rule-based and LLM-based method to generate step-by-step SQL explanations based on the results . |
| Outcome: | The proposed framework outperforms models with the same model size on BIRD and Spider benchmarks. |
In-Context Reinforcement Learning with Retrieval-Augmented Generation for Text-to-SQL (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods of synthetic query generation generate mostly simple queries which might not be sufficiently representative of complex, real world queries. |
| Approach: | They propose to use large language models to fine tune query generation to produce complex queries that practitioners may pose during inference. |
| Outcome: | The proposed framework achieves 15-20% higher recall in database/table retrieval task compared to the existing state-of-the-art models for schema identification and upto 2% higher execution accuracy for SQL generation. |
UR2 : Unify RAG and Reasoning through Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing attempts to unify large language models are limited to open-domain QA with fixed retrieval settings. |
| Approach: | They propose a general reinforcement learning framework that dynamically coordinates retrieval and reasoning. |
| Outcome: | The proposed framework outperforms existing paradigms on open-domain QA, MMLU-Pro, medical, and mathematical reasoning tasks. |
EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQL (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing RL methods assign query-level rewards to all clauses, treating correct and incorrect clauses equally. |
| Approach: | They propose a method which provides fine-grained supervision through clause-level rewards. |
| Outcome: | Experiments on widely-used Text-to-SQL benchmarks show that EXPO-SqL outperforms existing methods by fine-grained clause-level learning. |
Gen-SQL: Efficient Text-to-SQL By Bridging Natural Language Question And Database Schema With Pseudo-Schema (2025.coling-main)
Copied to clipboard
| Challenge: | Recent studies have shifted paradigms and leveraged Large Language Models (LLMs) to tackle the challenging task of Text-to-SQL. |
| Approach: | They propose a framework that leverages large language models to generate SQL queries . they exploit prior knowledge from the LLM to enhance embedding-based retriever . |
| Outcome: | The proposed method improves embedding-based retriever and reduces cost. |
R3-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL (2024.findings-emnlp)
Copied to clipboard
Yuhang Zhou, Yu He, Siyu Tian, Yuchen Ni, Zhangyue Yin, Xiang Liu, Chuanjun Ji, Sen Liu, Xipeng Qiu, Guangnan Ye, Hongfeng Chai
| Challenge: | Adapting existing approaches for converting natural language to SQL encounters hurdles due to distinct nature of GQL compared to SQL. |
| Approach: | They propose a method that integrates both small and large Foundation Models for ranking, rewriting, and refining tasks. |
| Outcome: | The proposed approach integrates both small and large Foundation Models for ranking, rewriting, and refining tasks while capitalizing on the superior generalization and query generation prowess of larger models for the final transformation of natural language queries into GQL formats. |