ExpWeaver: LLM Agents Learn from Experience via Latent RAG

ArXi:2606.01041v1 Announce Type: new Experience learning has achieved promising results in enhancing LLM agent planning and reasoning by integrating past interactions as reusable knowledge. However, existing methods remain confined to explicit text space, retrieving experiences via semantic similarity and concatenating them into the context window, leading to substantial token overhead and a decoupled architecture that separates retrieval from generation.