Continual Learning Bench
Explore score history ↗Evaluates continual learning in LLM-based systems across six expert-validated domains with stateful tasks sharing learnable latent structure.
- Released
- 2026-06-04
- Institutions
- University of California, Berkeley · University of Wisconsin–Madison
- Evaluates
- General AI, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
Continual Learning Bench paper
No reported scores are on record for this benchmark yet.