EP267: AI Agents That Update Their Own Imagination

Title: COMAP: Co-Evolving World Models and Agent Policies for LLM AgentsSource: http://arxiv.org/abs/2606.02372v1Summary:COMAP proposes a novel architectural primitive where textual world models and agent policies co-evolve through closed-loop interaction and self-distillation. This framework enables agents to adapt to dynamic environments by predicting future states and reflecting on action reliability, significantly improving long-horizon decision-making.