# 首个文本转SQL模型超越人类基准

- 来源：Thinking Machines (@thinkymachines)
- 发布时间：2026-08-28 07:40
- AIHOT 分数：35
- AIHOT 链接：https://aihot.virxact.com/items/cmtc64unj01pcrojqm3dm3xel
- 原文链接：https://x.com/thinkymachines/status/2093121414656377160

## AI 摘要

Thinking Machines与UIUC、Bridgewater研究人员合作，将专家判断融入RLVR的每个环节，训练出首个在文本转SQL任务上超越人类基准的模型。该方法需前期投入数据清洗与奖励函数对齐，但最终在复杂任务上达到SOTA水平。

## 正文

Cleaning data and aligning the reward function for RLVR takes expertise and effort upfront, but the result is a model that's state-of-the-art on a complex task.

Guest post by researchers at UIUC and Bridgewater, in collaboration with our team.
https://thinkingmachines.ai/news/putting-task-expertise-into-rl

### 引用推文

> Tinker：LLMs with scaffolds have lagged on text-to-SQL, a task that relies on human judgment. By folding expert judgment into every part of RLVR on Tinker, @maxYuxuanZh...