English(EN) DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learning

DualSQL系统使用多智能体RL提高文本到SQL性能

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-17 04:00

研究人员开发了DualSQL，一个新颖的文本到SQL系统，它使用单一模型骨干和两个智能体进行联合优化。这个多智能体强化学习框架允许共享模型权重和智能体脚手架，从而在复杂的数据库查询上获得更好的性能。DualSQL-4B在BIRD开发集上实现了68.0%的执行准确率，与之前较大的模型相当，而DualSQL-8B达到了71.1%，超过了最先进的单一模型解决方案。 AI

影响这种方法可能带来更高效、更准确的文本到SQL系统，从而提高数据分析能力。

排序理由该集群描述了一篇详细介绍新AI系统及其在基准测试上性能的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇详细介绍新AI系统及其在基准测试上性能的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Shijie Chen, Yu Gan, Yeounoh Chung, Jiani Zhang, Quannan Li, Sravan Babu Bodapati, Cody J. Greer, Yu Su, Fatma Ozcan · 2026-09-17 04:00

DualSQL：多智能体强化学习的文本到SQL

arXiv:2609.18135v1 Announce Type: cross Abstract: 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 each task, failing to leverage th…

本文如何被排名

报道来源 [1]

DualSQL：多智能体强化学习的文本到SQL

相关实体

相关话题