# Google 论文：Co-Scientist 可靠性模块将论文结果幻觉率从 46% 降至 4%

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-09-01 12:29
- AIHOT 分数：64
- AIHOT 链接：https://aihot.virxact.com/items/cmti6sn5u0bxirofqjuluyhec
- 原文链接：https://x.com/rohanpaul_ai/status/2094643661707649169

## AI 摘要

Google DeepMind 论文《Accelerating Scientific Research with Gemini in the Real-World》（arxiv.org/abs/2608.26701）显示。

## 正文

New Google paper shows that autonomous AI research can go badly wrong even when the final paper looks convincing:

severe result hallucinations appeared in 90% of Agent Laboratory papers and 46% of Co-Scientist papers when its reliability modules were removed.

With Co-Scientist checking manuscript claims against the actual execution logs, that rate dropped to just 4%, and complete data fabrication fell to 0%.

– arxiv. org/abs/2608.26701

Title: "Accelerating Scientific Research with Gemini in the Real-World"