Article may be outdated

This article is 37 days old. Some details may have changed since publication.

Hacker News·4 min read·hard

Schema Harness Achieves ~99% on Arc‑AGI‑3 Public

J
jasondavies
AI Summary

A new framework called Schema has significantly improved the performance of AI models on the ARC-AGI-3 benchmark. By optimizing the process of how models interact with game environments, it achieved a 99% success rate on public sets.

Why it matters

This demonstrates that architectural process improvements can yield massive performance gains in AI reasoning without needing to retrain underlying model weights.

Dive DeeperCreate a free account to unlock

ARC‑AGI‑3 gives an agent a game environment, without an explanation of what it is seeing. At each step, the agent receives a 64×64 grid of 16 color indices and a set of legal actions. The environment supplies no object list, rule sheet, stated goal, or shaped reward. There is only one way to make progress: the physicist’s way. The agent must act while its model of the game is still provisional, forming hypotheses about what the grid represents, how actions change it, and what counts as success, then revising both its model and its plan as new observations arrive.

Continue reading on Headlinne

Create a free account to read the full article.

Read full article →
technologyscience
Political Bias
Center
LeftLean LCenterLean RRight
Confidence: 85%

Technical reporting on AI benchmarks with no political or social agenda.

Get smarter about the news

Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.

Create free account

Already have an account? Sign in