Salesforce 团队训练 8B 推理模型生成多样研究想法，创意效用得分超 Claude Opus 4.8 和 GPT-6 Astra
Salesforce 及合作者训练一个 8B 推理模型，一次生成多条研究想法，以缓解 AI 科研流水线难以提出新颖多样想法的问题。其奖励对整组想法打分，按每条想法与此前想法的距离加权质量，促使模型让新想法远离已有想法。
Great application of small language models from Salesforce and colleagues.
AI-scientist pipelines are well known to struggle to propose novel and diverse research ideas.
This team trains an 8B reasoning model to write several research ideas in one generation from a set of source papers.
The reward scores the whole set, weighting each idea's quality by how far it sits from the ideas written before it. The model learns to move each new idea away from the earlier ones.
On their contamination-free benchmark, the 8B model scores higher on creative utility, a measure that combines quality and diversity, than Claude Opus 4.8 and GPT-6 Astra.
arxiv.org/abs/2610.22324
Chat with Paper: academy.dair.ai/papers/train…
来源：omarsar0 · x.com