EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQL

Text-to-SQL enables users to query databases using natural language by generating executable SQL queries. Recent methods have increasingly adopted Large Language Models based reinforcement learning (RL) to leverage execution feedback for training. However, existing RL methods assign uniform query-level rewards to all clauses in a SQL query, treating correct and incorrect clauses equally. This coarse-grained reward design leads to insufficient learning signals for correct SQL generation. To address this issue, we propose EXPO-SQL (EXecution-based clause-level Policy Optimization for Text-to-SQL) which provides fine-grained supervision through clauselevel rewards. To assign clause-level rewards, our method identifies erroneous clauses by analyzing execution results, including error messages and clause-wise incremental execution. Experiments on widely-used Text-to-SQL benchmarks demonstrate that EXPO-SQL significantly outperforms existing supervised fine-tuning, prompting, and RL-based methods through fine-grained clause-level learning. Our code is available at https://github. com/jhn25/EXPO-SQL . * Corresponding authors SELECT COUNT() FROM location GROUP BY street_name 𝑆𝑄𝐿 1 SELECT street_name FROM location_street GROUP BY street ORDER BY COUNT() DESC LIMIT 1 𝑆𝑄𝐿 n -0.5 -0.5 LLM RL-Trainer ⋮ Query-level reward SELECT street_name FROM location_street GROUP BY street ORDER BY COUNT(*) DESC LIMIT 1