Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.22934 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913059726950400 |
|---|---|
| author | Parekh, Tanmay Hofmann-Coyle, Ella Wang, Shuyi Kothur, Sachith Sri Ram Prasad, Srivas Chen, Yunmo |
| author_facet | Parekh, Tanmay Hofmann-Coyle, Ella Wang, Shuyi Kothur, Sachith Sri Ram Prasad, Srivas Chen, Yunmo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_22934 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PExA: Parallel Exploration Agent for Complex Text-to-SQL Parekh, Tanmay Hofmann-Coyle, Ella Wang, Shuyi Kothur, Sachith Sri Ram Prasad, Srivas Chen, Yunmo Artificial Intelligence Computation and Language 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. |
| title | PExA: Parallel Exploration Agent for Complex Text-to-SQL |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2604.22934 |