Continual-ARC, a new continual learning benchmark for agents, lands on Hugging Face

NielsRogge · x · 2026-11-19

Unify released the dataset for Continual-ARC, a new continual learning benchmark built on ARC-style tasks, on Hugging Face (2,785 rows; configs include 2,400 instances, 260 arc3, 125 tasks, with multiple workstreams/sequential/random splits). It targets evaluating agents' lifelong learning abilities, with an associated paper (arXiv 2611.14505) under Apache-2.0/MIT licenses.

Original post →

More from Research

Research channel →