dataset
active
dataset:arc-agi-1-abstract-reasoning-corpusARC-AGI-1 (Abstract Reasoning Corpus)
Visual-puzzle benchmark used with TRM to probe fractal basins, and cited as evidence for reasoning models' efficiency.
Neighborhood — ranked by edge-count
Papers (1)
paper
Thinkers (1)
thinker
- François CholletintroducesCreator of the Abstract Reasoning Corpus (ARC-AGI), the benchmark used to motivate reasoning-model efficiency claims.
Methods (2)
method
- Cited small (7M param) recurrent model that outperforms >10B-parameter LLMs on ARC-AGI, motivating the paper's focus on reasoning dynamics.
- Architecture used to probe ARC-AGI-1 visual puzzle basins.