Google Research Introduces Retrieve-for-Train (R4T): An RL-Compiled Diffusion Retriever for 12× to 20× Faster Query Fan-Out

Google Research introduced Retrieve-for-Train (R4T), a search framework that trains a fan-out language model with reinforcement learning once, then uses that model to synthesize training data for a 53.9M-parameter diffusion retriever that generates all retrieval directions in a single pass, running 12× to 20× faster than autoregressive fan-out. The fan-out language model is trained with groundedness, diversity, and alignment rewards to return coherent, diverse result sets. No code or model weights have been released yet.

Google Research has introduced Retrieve-for-Train R4T , a framework for search that returns coherent, diverse result sets. It trains a fan-out language model with RL once, using groundedness, diversity, and alignment rewards. That model then synthesizes training data for a 53.9M-parameter diffusion retriever. The retriever generates all retrieval directions in a single pass, running 12× to 20× faster than autoregressive fan-out. No code or model weights have been released yet. The post Google Research Introduces Retrieve-for-Train R4T : An RL-Compiled Diffusion Retriever for 12× to 20× Faster Query Fan-Out https://www.marktechpost.com/2026/09/16/google-research-introduces-retrieve-for-train-r4t-an-rl-compiled-diffusion-retriever-for-12x-to-20x-faster-query-fan-out/ appeared first on MarkTechPost https://www.marktechpost.com .