paper-with-me

Papers

SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback

2026-05-31 · Leo Luo, Haining Xie, Siqi Shen, Zhipeng Ma, Rui Ling, Hang Xu, Hefeng Jiang, Dingwei Chen, Yang Li, Peng Chen, Jie Jiang arxiv

Text-to-SQL on complex schemas is unreliable on a single pass, so recent systems generate multiple SQL candidates and let voting filter out errors. Yet voting alone is not enough, because the multi-candidate recipe has three coupled weaknesses: 1) sampling more from a single generator produces increasingly redundant candidates, 2) existing pipelines apply one generic correction to every non-clean execution result, while runtime errors, timeouts, and empty results each indicate a different distance from correctness, and 3) existing selectors rely on a single angle such as result-majority voting or pairwise SQL comparison, missing what other angles would have caught. We present SIRIUS-SQL, which addresses all three weaknesses. A difficulty-smoothing RL recipe trains SIRIUS-32B to generate diverse executable SQL candidates, paired with a generalist LLM that fills in gaps left by the specialist. An execution-grounded lifecycle classifies each outcome and applies targeted repair before candidates re-enter the pool. A confidence-gated hybrid selector combines execution-result agreement with pairwise SQL-form judgment, escalating only near-tied cases to a deterministic structural check. SIRIUS-SQL reaches 75.88% on BIRD dev and 91.20% on SPIDER test. Two of three generalist pairings surpass Agentar-Scale-SQL, the strongest published multi-candidate system on BIRD dev.

📄 PDF Abstract BibTeX arXiv:2606.01246

Code (0)

등록된 구현이 없습니다.

Results from the Paper

RankTaskDatasetModelMetrics
#2 Text-To-SQL SPIDER SIRIUS-SQL Exact Match Accuracy (in Dev): 75.88
#2 Text-To-SQL spider SIRIUS-SQL Execution Accuracy (Test): 91.20

Similar Papers 제목 키워드 기반

SiriusHelper: An LLM Agent-Based Operations Assistant for Big Data Platforms

2026-04-29 · Yu Shen, Shiyang Liu, Qihang He, Yihang Cheng 외 arxiv

Big data platforms are widely used in modern enterprises, and an in-production intelligent assistant is increasingly important to help users quickly find actionable guidance and reduce operational burden. While recent LL…

Sirius: Contextual Sparsity with Correction for Efficient LLMs

2024-09-05 · Yang Zhou, Zhuoming Chen, Zhaozhuo Xu, Victoria Lin 외

With the blossom of large language models (LLMs), inference efficiency becomes increasingly important. Various approximation methods are proposed to reduce the cost at inference time. Contextual Sparsity (CS) is appealin…

Math

Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment

2022-11-15 · Huihan Liu, Soroush Nasiriany, Lance Zhang, Zhiyao Bao 외

With the rapid growth of computing powers and recent advances in deep learning, we have witnessed impressive demonstrations of novel robot capabilities in research settings. Nonetheless, these learning systems exhibit br…

Contact-rich ManipulationDecision Making

Multi-Task Interactive Robot Fleet Learning with Visual World Models

2024-10-30 · Huihan Liu, Yu Zhang, Vaarij Betala, Evan Zhang 외

Recent advancements in large-scale multi-task robot learning offer the potential for deploying robot fleets in household and industrial settings, enabling them to perform diverse tasks across various environments. Howeve…

SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning

2025-02-07 · Wanjia Zhao, Mert Yuksekgonul, Shirley Wu, James Zou

Multi-agent AI systems powered by large language models (LLMs) are increasingly applied to solve complex tasks. However, these systems often rely on fragile, manually designed prompts and heuristics, making optimization …