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.
More from Research
- MIT CSAIL paper: frozen LLM agents design their own self-improvement without being told how — omarsar0 · 2026-11-19
- Radiology benchmark RadLE is 100% human-verified; RadLE 2.1 results coming at RSNA — DrDatta_AIIMS · 2026-11-19
- Anthropic Says Claude Solved Two Open Problems in Black Hole Physics — ghumare64 · 2026-11-19
- Shu Ding's essay 'Metaphors': protocols, dimensional analysis, and Curry-Howard — shuding · 2026-11-19
- Why your fine-tuning job takes longer than the FLOPs say — Hugging Face Blog · 2026-11-19
- CyberArena benchmark: Lithos defense agent wins 3-0, blocking 12 of 12 attacks — JiaZhihao · 2026-11-19