TRUST‑SQL tackles Text‑to‑SQL parsing in environments where the full database schema is unknown, a common scenario in enterprise settings with many noisy tables. The method models the problem as a Partially Observable Markov Decision Process and uses a four‑phase protocol to verify only relevant metadata, guided by a Dual‑Track GRPO strategy that separates exploration from execution rewards. Experiments on five benchmarks show significant gains, with the 4B and 8B variants outperforming base models by 30.6% and 16.6% respectively, while matching or exceeding baselines that rely on pre‑loaded schemas.
arXiv:2603.20004v4 Announce Type: replace-cross Abstract: Translating natural language questions to SQL queries (Text-to-SQL) is a long-standing problem in database research. Recent efforts have focu...
DualSQL is a Text-to-SQL system that uses two agents sharing a single model backbone, enabling joint optimization via multi-agent reinforcement learning. The approach incorporates three database access tools for multi-step reasoning, rollout guardrails to stabilize training, and a new SQL correctness metric called robust execution match (REX). Trained on only 3,755 examples, DualSQL-4B reaches 68.0% execution accuracy on the BIRD dev set, while DualSQL-8B achieves 71.1%, surpassing prior state‑of‑the‑art single‑model solutions with 32B parameters.
State-of-the-art Text-to-SQL systems are typically multi-agent pipelines centered around two fundamental tasks: schema linking and SQL generation. However, existing work trains separate models for eac...
arXiv:2602. 16720v2 Announce Type: replace-cross Abstract: Text-to-SQL systems powered by Large Language Models have excelled on academic benchmarks but struggle in complex enterprise environments.
SERL‑SQL introduces a selective execution‑grounded reinforcement learning framework for multi‑turn Text‑to‑SQL agents. It samples on‑policy interaction trajectories and employs a training‑only teacher to re‑score student actions using execution feedback, converting the teacher‑student likelihood gap into bounded, masked weights that reweight GRPO advantages only on SQL and tool‑action tokens. Experiments on BIRD, Spider, and cross‑domain benchmarks show competitive performance, achieving 76.56% execution accuracy on BIRD‑Dev and 89.92% on Spider‑Test, and the reward‑based selection strategy approaches the oracle Best‑of‑N upper bound.
arXiv:2505. 04671v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) trained with reinforcement learning (RL) have improved Text-to-SQL performance.
The paper introduces the DevRev NL2SQL benchmark, featuring 900 execution‑verified queries that test natural‑language‑to‑SQL systems on nested, graph‑like enterprise schemas, and proposes the Semantic Depth Score (SDS) as a rubric for analytical reasoning depth. It also presents a cost‑aware, single‑generation agentic architecture that includes schema selection, metadata retrieval, and error‑repair components tailored to these complex schemas. On the DevRev benchmark, the system achieves 91.7% answer correctness, outperforming the next‑best baseline by 54.6 percentage points, and remains competitive on the Spider 2.0 Snowflake dataset.
HarnessSQL introduces a harness‑native post‑training framework that keeps the full stateful, multi‑turn interaction structure of real‑world database agents during both supervised fine‑tuning and reinforcement learning. By building isolated executable database environments with hidden execution oracles and retaining only verified trajectories for full‑sequence SFT, the method enables execution‑reward RL that aligns training with inference. Experiments on Spider 2.0‑SQLite show dramatic gains in execution accuracy for compact models, and the approach transfers effectively to out‑of‑distribution interactive benchmarks such as BIRD‑Interact and LiveSQLBench.
The paper introduces Verifiable Process Rewards (VPR), a framework that uses symbolic or algorithmic task-solving oracles as action-level verifiers to provide dense rewards for intermediate actions in agentic reasoning tasks. VPR is applied to Sokoban, Sudoku, and Minesweeper, and improves policy performance over outcome-reward baselines. The authors also demonstrate VPR’s effectiveness in a tool‑use benchmark, highlighting its reliance on reliable task oracles and the difficulty of extending it to less structured environments.
arXiv:2607. 14494v1 Announce Type: new Abstract: Complex knowledge base question answering (KBQA) is commonly approached through either information retrieval over a question-specific subgraph or semantic parsing into an executable logical form.
arXiv:2606. 28601v1 Announce Type: cross Abstract: Recent progress in Text-to-SQL has been driven by stronger language models and prompting strategies, yet performance on real enterprise benchmarks such as Spider 2.
BIRD‑RL is a new agentic reinforcement learning framework designed to scale training of small language models (SLMs) in data‑centric, stateful environments such as SQL debugging. It introduces a four‑stage curriculum that alternates between improving agent reasoning and trajectory‑adaptive exploration, and relies on a Trajectory‑scoped Persistent Execution Infrastructure to safely reuse database replicas while maintaining trajectory isolation. This approach yields a 12.8× improvement in spatial efficiency and enables 7B and 14B models to achieve competitive success rates on the BIRD‑CRITIC‑SQLite benchmark, matching proprietary agents like Claude‑Opus‑4.6.