A project called ARC-AGI-2 has achieved a 20.7% score using zero neural networks, focusing on LLM-free symbolic reasoning. The initiative also includes innovative iOS games controlled by mouth movemen…
Researchers present ARCANA, a collaborative multi-agent framework for solving ARC-AGI-2 tasks under strict test-time and hardware constraints. The framework decomposes tasks into iterative perception,…
Researchers introduced Regressive Plasticity Schedule (RPS), a two-stage post-training schedule that couples a learning-rate drop with a curriculum boundary between easier and harder data. Testing on …
A researcher built a model with a single parameter that achieved 100% accuracy on the ARC-AGI-2 benchmark, a million-dollar challenge designed to test reasoning models. The model used chaos theory and…