Salesforce 8B 模型创意多样性超过 GPT-6 Astra
Salesforce 训练 8B 推理模型一次生成多个研究想法，用「与前面想法距离」加权奖励提升多样性，在无污染基准上创意效用超过 Claude Opus 4.8 和 GPT-6 Astra。
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. https://arxiv.org/abs/2610.22324 Chat with Paper: https://academy.dair.ai/papers/training-reasoning-models-to-generate-diverse-scientific-ideas-2610.22324