LEAF-SQL uses level-wise exploration with adaptive fine-graining and dual agents to generate diverse SQL skeletons, reaching 71.6% execution accuracy on the BIRD benchmark and outperforming prior search- and skeleton-based methods.
Canonical reference
Sql-o1: A self-reward heuristic dynamic search method for text- to-sql
Canonical reference. 80% of citing Pith papers cite this work as background.
8
Pith papers citing it
Background
80% of classified citations
citation-role summary
background 4
method 1
citation-polarity summary
years
2026 8representative citing papers
EXPO-SQL improves Text-to-SQL by using clause-level rewards derived from execution error messages and incremental clause execution instead of uniform query-level rewards.
NL2SQLBench is a new modular benchmarking framework that evaluates LLM NL2SQL methods across three core modules on existing datasets, exposing large accuracy gaps and computational inefficiency.
SQLConductor uses Search-to-Policy Learning with MCTS, stability-weighted SFT, and curriculum RL to train a compact policy for adaptive step-wise Text-to-SQL orchestration, reporting 73.2% EX on BIRD-Dev.
FINER-SQL boosts 3B-parameter small language models to 67.73% and 85% execution accuracy on BIRD and Spider benchmarks via dense memory and atomic rewards in group relative policy optimization, matching larger LLMs at lower latency.
A literature survey that taxonomizes methods, datasets, and evaluation practices for natural language interfaces to geospatial and temporal databases while identifying recurring trends and future directions.
APMPO boosts average Pass@1 scores on math reasoning benchmarks by 3 points over GRPO by using an adaptive power-mean policy objective and feedback-driven clipping bounds in RLVR training.
FREIA applies free energy principles and adaptive advantage shaping to unsupervised RL, outperforming baselines by 0.5-3.5 Pass@1 points on math reasoning with a 1.5B model.
citing papers explorer
-
Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning
APMPO boosts average Pass@1 scores on math reasoning benchmarks by 3 points over GRPO by using an adaptive power-mean policy objective and feedback-driven clipping bounds in RLVR training.