Set-level RL with distance-weighted scoring teaches models to generate diverse ideas without sacrificing quality—a 8B model beats much larger models on ideation tasks by optimizing for both novelty and feasibility together.
This paper trains LLMs to generate diverse, high-quality scientific ideas from research papers using set-level reinforcement learning. Instead of optimizing individual ideas, the model generates K structured idea cards where each new idea is weighted by its distance from previous ones, encouraging diversity.