AI RESEARCH
Probabilistic Tiny Recursive Model
arXiv CS.AI
•
ArXi:2605.19943v1 Announce Type: new Tiny Recursive Models (TRM) solve complex reasoning tasks with a fraction of the parameters of modern large language models (LLMs) by iteratively refining a latent state and final answer. While powerful, their deterministic recursion can lead to convergence at suboptimal solutions, without escape mechanism. A common workaround relies on task-specific input perturbations at test time combined with answer aggregation via voting. We