Amin Sghaier, Ali Parviz, and Alexia Jolicoeur-Martineau introduce Probabilistic Tiny Recursive Models, a train-free extension to Tiny Recursive Models that reaches 91.2 percent accuracy on PPBench puzzles

Very cool train-free extension to TRM. By injecting noise into the latent space, TRMs can explore a wider set of basins, and the exit head can then identify which trajectories succeeded. Feels like unlocking an entirely new scaling axis. Awesome work! 🔗https://arxiv.org/pdf/2605.19943