{"slug": "acts-sql-agentic-and-critic-oriented-tree-structured-sql-correctness-with-large", "title": "ACTS-SQL: Agentic and Critic-Oriented Tree-Structured SQL Correctness with Large Language Models", "summary": "A training-free framework called ACTS-SQL, developed by researchers and deployed in Volcano Engine's Torch Log Service (TLS), improves SQL execution accuracy from 36.77% to 53.61% on real user queries using GPT-5, and achieves a 9.42% improvement over the previous state-of-the-art on the BIRD-Critic benchmark.", "body_md": "arXiv:2608.15145v1 Announce Type: new\nAbstract: Large Language Models (LLMs) have been increasingly adopted in Text-to-SQL systems, yet SQL errors remain a major obstacle in real-world Text-to-SQL inference pipelines. Existing SQL correction approaches either rely on large-scale, high-quality training data with substantial overhead, or adopt single-path agentic workflows that are brittle to early mistakes and prone to error propagation.\nTo develop a practical SQL correctness system for industrial scenarios, we present a training-free framework that formulates SQL correction as a plan-guided, tree-structured debugging process. By maintaining multiple correction strategies and enabling backtracking, the framework mitigates error accumulation during iterative refinement. We further integrate execution-based verification and clause-level diagnostic tools to support strategy pruning and precise error localization.\nWe evaluate the system on the BIRD-Critic benchmark and observe consistent accuracy gains over strong LLM backbones and representative agent-based baselines, achieving a 9.42% improvement over the previous state-of-the-art method. The framework is also deployed in the Torch Log Service (TLS) of Volcano Engine to support an online Text-to-TLS API. In production, it improves execution accuracy from 36.77% to 53.61% on real user queries with a representative strong LLM backbone (GPT-5). These results demonstrate the effectiveness and stability of our approach in real-world deployments.", "url": "https://wpnews.pro/news/acts-sql-agentic-and-critic-oriented-tree-structured-sql-correctness-with-large", "canonical_source": "https://www.machinebrief.com/news/acts-sql-agentic-and-critic-oriented-tree-structured-sql-cor-y4q7", "published_at": "2026-08-18 04:00:00+00:00", "updated_at": "2026-08-18 05:40:52.912283+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-research"], "entities": ["ACTS-SQL", "Volcano Engine", "Torch Log Service", "BIRD-Critic", "GPT-5"], "alternates": {"html": "https://wpnews.pro/news/acts-sql-agentic-and-critic-oriented-tree-structured-sql-correctness-with-large", "markdown": "https://wpnews.pro/news/acts-sql-agentic-and-critic-oriented-tree-structured-sql-correctness-with-large.md", "text": "https://wpnews.pro/news/acts-sql-agentic-and-critic-oriented-tree-structured-sql-correctness-with-large.txt", "jsonld": "https://wpnews.pro/news/acts-sql-agentic-and-critic-oriented-tree-structured-sql-correctness-with-large.jsonld"}}