Amazon 论文：LLM 可作研究世界模型预测训练收益
New Amazon paper shows that an LLM can act as a research world model, predicting whether a training change will help before anyone spends GPU time on it.
Amazon 新论文让 LLM 充当研究世界模型，在消耗 GPU 前预测训练改动是否有效。基于 9 个场景的 2653 条真实实验记录测试，加入同场景历史记录后，5 个场景的平均排名相关性从 0.506 升至 0.774；OLMo3-100M 场景下低推理强度加记录得 0.892，最高强度无记录仅 0.648。作者建议研究智能体记录包括失败在内的每次实验，并喂给挑选下一次运行的模型。
正文
当前显示原文，中文全文译文尚未就绪。
New Amazon paper shows that an LLM can act as a research world model, predicting whether a training change will help before anyone spends GPU time on it.
AI research agents can propose experiments far faster than teams can afford to run them. Choosing what gets GPU time means guessing outcomes in advance.
They used an LLM as a research world model that predicts an experiment's gain before it runs. They tested it on 2,653 real experiment records from 9 setups, from pretraining to inference.
Past records from the same setup raised average ranking correlation with actual results from 0.506 to 0.774 across 5 setups. On the OLMo3-100M setup, adding records at low reasoning effort scored 0.892, while max effort without records reached 0.648.
If you run research agents, log every experiment, including failures, and feed those records to whatever model picks the next run.