CL-Bench is the first expert-validated benchmark for continual learning in frontier LLMs across six real-world domains, showing limited gains and that naive in-context learning outperforms dedicated memory systems.
Wołczyk, M
3 Pith papers cite this work, alongside 20 external citations. Polarity classification is still indexing.
3
Pith papers citing it
20
external citations · external index
years
2026 3representative citing papers
Continual learning robots form a significantly more stable invariant subnetwork than constant-task controls, and preserving it improves adaptation while damaging it hurts performance.
Relative rankings of online EWC, LwF, SI and GEM are not consistently preserved across five trainable-depth regimes on five datasets and eleven task orders.
citing papers explorer
-
Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments
CL-Bench is the first expert-validated benchmark for continual learning in frontier LLMs across six real-world domains, showing limited gains and that naive in-context learning outperforms dedicated memory systems.
-
Evidence of an Emergent "Self" in Continual Robot Learning
Continual learning robots form a significantly more stable invariant subnetwork than constant-task controls, and preserving it improves adaptation while damaging it hurts performance.
-
Fine-Tuning Regimes Define Distinct Continual Learning Problems
Relative rankings of online EWC, LwF, SI and GEM are not consistently preserved across five trainable-depth regimes on five datasets and eleven task orders.