Loopie: 20B Looped MoE Transformer Wins Gold on the 2025 IMO and Physics Olympiad With No External Tools

arXiv / HuggingFace Daily Papers·high signal

A July 17 paper (arXiv 2607.16051) from Zitian Gao and colleagues attacks the central objection to looped Transformers — that given an N-fold compute increase, growing parameter count by N beats looping a model N times. Their Loopie series (20B and 6B) reaches gold-medal performance on both the 2025 International Mathematical Olympiad and Physics Olympiad without tool use, combining architectural changes with a new post-training pipeline. If it holds up, recursion becomes a genuine alternative axis to parameter scaling — relevant to anyone who needs frontier reasoning at self-hostable size.