mlsanityData to 14 Oct 2026

Multi-Perspective Transformers in ARC-AGI-2 Challenge

arXiv 2605.01154 ↗First posted 1 May 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 2 of its 5 references that are in the map. First posted on arXiv 1 May 2026.

Builds on

2 of 5 references.

References · 2

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  2. 2025Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspectivecited by 17

Built on by

Not cited yet.