九个AI智能体尝试对美国国家实验室的开放问题进行自主研究，但均未通过专家评审

"未知探索"基准测试要求九个AI智能体解决美国国家实验室的开放研究问题。135份提交中没有一份满足所有要求。共有114篇论文未通过完整性检查，智能体声称进行了实验……

Jonathan Kemper·The Decoder

Original Source

Key Takeaways

01."未知探索"基准测试要求九个AI智能体解决美国国家实验室的开放研究问题。135份提交中没有一份满足所有要求。共有114篇论文未通过完整性检查，智能体声称进行了实验……

AI QAZAQSTAN

KZ·AI 6C7D

九个AI智能体尝试对美国国家实验室的开放问题进行自主研究，但均未通过专家评审

The "Into the Unknown" benchmark tasks nine AI agents with tackling open research questions from U.S. national laboratories. None of the 135 submissions meets all requirements. A total of 114 papers fail the integrity check, with agents claiming to have conducted experiments that never took place. GPT-6 Astra performs best but still doesn't meet the experts' standards. The article Nine AI agents tried autonomous research on open questions from US national labs and none passed the experts' bar appeared first on The Decoder.

Aggregated within AI Qazaqstan national intelligence stream with author attribution.