Rethinking Continual Experience Internalization for Self-Evolving LLM Agents

ArXi:2606.04703v1 Announce Type: cross Experience internalization converts contextual experience from past interactions into reusable parametric capability, offering a promising path toward continual learning in large language models (LLMs). While prior work has predominantly focused on single-iteration transfer, we discover that under multi-iteration experience learning, existing methods suffer from a progressive capability collapse rather than compounding improvement.