Model Releases
Great application of small language models from Salesforce and colleagues. AI-scientist pipelines are well known to struggle to propose nove…
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 reasoni
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
Related
- Another great paper from Salesforce AI Research. The finding is that a 31B open Gemma-4 web agent scores 74.6% on the 9-app WebArena Infinit…
- Nice paper from Salesforce on co-evolving harnesses and models. Harness engineering is a hot topic right now. So this is a great read. (book…
- Banger report from Salesforce. Pretty interesting to see more of these custom enterprise models. Salesforce trained the enterprise agent mod…
Source: DAIR.AI (X) | 2026-10-17