Google提出DualSQL多智能体训练方法

这两个智能体共享相同模型权重，通过多智能体强化学习共同训练。DualSQL-4B模型在仅3,755个样本训练后，在BIRD dev基准上达到68.

0%执行准确率，与早期7B模型相当；DualSQL-8B达到71.

1%，超越32B参数的单模型系统。

Great paper from Google and colleagues. Trains Text-to-SQL agents using multi-agent RL. (bookmark it) This work proposes DualSQL, which splits Text-to-SQL into two agents, one that links the question to the right tables and columns and one that writes the SQL. Both agents run on the same model weights, so a single multi-agent RL run trains both roles together. The agents can query the database through three tools while they reason. Multi-agent RL tends to collapse during training, so the authors add guardrails on rollouts and a new reward, robust execution match, that judges SQL correctness more accurately. Trained on only 3,755 examples, DualSQL-4B reaches 68.0% execution accuracy on BIRD dev, matching earlier 7B models. DualSQL-8B reaches 71.1%, ahead of previous single-model systems with 32B parameters. Paper: arxiv.org/abs/2609.18135 Chat with Paper: academy.dair.ai/papers/dualsql…📊 1 ⚡

本条情报归属 AITOP「论文」核心栏目，重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：DualSQL、Text-to-SQL、多智能体、强化学习，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明：本文原始线索采编自「elvis」（@omarsar0），经 AITOP 多维评分管线结构化提炼。