Tag
Proposes Experience Distillation, a method that internalizes in-context learning gains from agent interaction histories into model weights without requiring additional environment interaction, achieving significant sample efficiency improvements on software engineering and text-adventure tasks.
This paper formulates context distillation as a latent memory management problem, proposing a framework that stores distilled contexts as independent LoRA adapters with retrieval, routing, and self-gating to improve robustness and efficiency.