Paper summary
Paper summary: Less is More: Recursive Reasoning with Tiny Networks
Tiny Recursive Model, a single 2-layer network with 7M parameters that repeatedly refines its answer, reports 45% on ARC-AGI-1 and 8% on ARC-AGI-2, above many large LLMs on these puzzles.
- A 7M-parameter network that recursively improves its own answer beats much larger LLMs on ARC-AGI puzzles.
- It simplifies the earlier Hierarchical Reasoning Model (two networks at two speeds) into one tiny network.