Scaling Self-Evolving Agents via Parametric Memory

ArXi:2606.04536v1 Announce Type: new Existing memory-augmented LLM agents past experience exclusively in prompt space, as textual summaries or retrieved passages, while keeping model parameters frozen throughout a rollout. Such agents can \emph{look up} what they have seen but cannot \emph{learn from} it: their policy is unchanged by experience, and any information dropped from the context is permanently lost. We