IESR:Efficient MCTS-Based Modular Reasoning for Text-to-SQL with Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910012709797888 |
|---|---|
| author | Liu, Tao Lu, Jiafan Yu, Bohan Wu, Pengcheng Haixin, Liu Xu, Guoyu Xiangheng, Li Li, Lixiao Hou, Jiaming Shijun, Zhao Lyu, Xinglin Zhang, Kunli Jia, Yuxiang Zan, Hongyin |
| author_facet | Liu, Tao Lu, Jiafan Yu, Bohan Wu, Pengcheng Haixin, Liu Xu, Guoyu Xiangheng, Li Li, Lixiao Hou, Jiaming Shijun, Zhao Lyu, Xinglin Zhang, Kunli Jia, Yuxiang Zan, Hongyin |
| contents | Text-to-SQL is a key natural language processing task that maps natural language questions to SQL queries, enabling intuitive interaction with web-based databases. Although current methods perform well on benchmarks like BIRD and Spider, they struggle with complex reasoning, domain knowledge, and hypothetical queries, and remain costly in enterprise deployment. To address these issues, we propose a framework named IESR(Information Enhanced Structured Reasoning) for lightweight large language models: (i) leverages LLMs for key information understanding and schema linking, and decoupling mathematical computation and SQL generation, (ii) integrates a multi-path reasoning mechanism based on Monte Carlo Tree Search (MCTS) with majority voting, and (iii) introduces a trajectory consistency verification module with a discriminator model to ensure accuracy and consistency. Experimental results demonstrate that IESR achieves state-of-the-art performance on the complex reasoning benchmark LogicCat (24.28 EX) and the Archer dataset (37.28 EX) using only compact lightweight models without fine-tuning. Furthermore, our analysis reveals that current coder models exhibit notable biases and deficiencies in physical knowledge, mathematical computation, and common-sense reasoning, highlighting important directions for future research. We released code at https://github.com/Ffunkytao/IESR-SLM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05385 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | IESR:Efficient MCTS-Based Modular Reasoning for Text-to-SQL with Large Language Models Liu, Tao Lu, Jiafan Yu, Bohan Wu, Pengcheng Haixin, Liu Xu, Guoyu Xiangheng, Li Li, Lixiao Hou, Jiaming Shijun, Zhao Lyu, Xinglin Zhang, Kunli Jia, Yuxiang Zan, Hongyin Computation and Language Text-to-SQL is a key natural language processing task that maps natural language questions to SQL queries, enabling intuitive interaction with web-based databases. Although current methods perform well on benchmarks like BIRD and Spider, they struggle with complex reasoning, domain knowledge, and hypothetical queries, and remain costly in enterprise deployment. To address these issues, we propose a framework named IESR(Information Enhanced Structured Reasoning) for lightweight large language models: (i) leverages LLMs for key information understanding and schema linking, and decoupling mathematical computation and SQL generation, (ii) integrates a multi-path reasoning mechanism based on Monte Carlo Tree Search (MCTS) with majority voting, and (iii) introduces a trajectory consistency verification module with a discriminator model to ensure accuracy and consistency. Experimental results demonstrate that IESR achieves state-of-the-art performance on the complex reasoning benchmark LogicCat (24.28 EX) and the Archer dataset (37.28 EX) using only compact lightweight models without fine-tuning. Furthermore, our analysis reveals that current coder models exhibit notable biases and deficiencies in physical knowledge, mathematical computation, and common-sense reasoning, highlighting important directions for future research. We released code at https://github.com/Ffunkytao/IESR-SLM. |
| title | IESR:Efficient MCTS-Based Modular Reasoning for Text-to-SQL with Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.05385 |