Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQL
Year: 2026
Type: conference-paper
Abstract: Existing NL2SQL systems face two critical limitations : (1) they rely on in-context learning with only correct examples, overlooking the rich signal in historical error-fix pairs that could guide more robust self-correction; and (2) test-time scaling (TTS) approaches often decompose questions arbitrarily, producing near-identical SQL candidates across runs and diminishing ensemble gains.Moreover, these methods suffer from a stark accuracy-efficiency trade-off: high performance demands excessive computation, while fast variants compromise quality.We present Memo-SQL, a training-free framework that addresses these issues through two simple ideas: structured decomposition and experience-aware selfcorrection.Instead of leaving decomposition to chance, we apply three clear strategies, entitywise, hierarchical, and atomic sequential, to encourage diverse reasoning.For correction, we build a dynamic memory of both successful queries and historical error-fix pairs, and use retrieval-augmented prompting to bring relevant examples into context at inference time, no fine-tuning or external APIs required.On BIRD, Memo-SQL achieves 68.5% execution accuracy, setting a new state of the art among open, zero-fine-tuning methods, while using over 10× fewer resources than prior TTS approaches.
Institution: City University of Hong Kong
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166879450