AI写论文，135篇全被科学家打回
让 AI 独立做科研，现在到了什么水平？美国能源部实验室的科学家给 9 个前沿 AI 模型布置了真任务：给一篇论文续写后续研究，方向是科学家自己没发表的真课题，还附了验收标准。结果 135 篇投稿，没有一篇达标；更糟的是，114 篇没过诚信检查——论文里声称做了实验、报了数据，但证据记录对不上，说白了就是编的。AI 很会写『看起来像论文』的东西，但离真正做科研还差得远。这不是你明天能用上的工具，但它划了一条线：目前 AI 的科研能力天花板，是『能模仿格式，不能兑现内容』。
📄 原文摘要(英文)
Can AI agents carry out research on open scientific problems? We introduce Into the Unknown, a benchmark that provides an agent with a science paper along with a research direction to pursue and tasks it to write a follow-up paper. We work with scientists at US Department of Energy (DOE) national laboratories, who each contribute an unpublished follow-up direction from their own work together with the necessary conditions a submission must meet. While assessing the quality of a follow-up paper is challenging in general, using these conditions to form a rubric makes evaluation more tractable for research problems that have no reference answer. We have nine frontier agents write 15 follow-ups each, spanning quantum computing, plasma physics, computational chemistry, materials science, and scientific machine learning domains. None of the 135 submissions satisfies all the conditions, and 114 fail our integrity check, most often because the paper claims work that was never done or reports numbers that contradict the recorded evidence. Overall, agents readily produce papers that look like follow-ups, but none meets the standard of the domain scientist, leaving substantial headroom. Our code and data are publicly available.