Scaling Discovery Requires Forgetting
Restarting LLM research agents by forgetting search history improves discovery by up to 39 percent versus one agent.
Stories per day · 30 days
3 stories, newest first · one card per story
Stories tagged #forgetting
Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss
A local learning interaction unifies data attribution, forgetting, and plasticity loss in continual updates.
Benchmarking World Models for Continual Learning on Compositional Tasks
A new compositional benchmark finds modular world models reuse robot skills better, but still forget.