English

Multi-Perspective Transformers in ARC-AGI-2 Challenge

Machine Learning 2026-05-05 v1 Artificial Intelligence

Abstract

ARC-AGI-2 is a benchmark of human-intuitive visual puzzles that measures a machine's ability to generalize from limited examples, interpret symbolic meaning, and flexibly apply rules in varying contexts. In this paper, we discuss our approach to solving the ARC-AGI-2 puzzles with TinyLM, with additional fine-tuning at test time, including Test-Time-Training (TTT) and Products of Experts (POE). Our model achieves 96.1% accuracy on the training set and 21.7% accuracy on the evaluation set.

Cite

@article{arxiv.2605.01154,
  title  = {Multi-Perspective Transformers in ARC-AGI-2 Challenge},
  author = {Caleb Talley and Vedant Tibrewal and Seun Adekunle and Weiwen Dong and Xinyu Wu and Fariha Sheikh},
  journal= {arXiv preprint arXiv:2605.01154},
  year   = {2026}
}
R2 v1 2026-07-01T12:46:08.082Z