RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection

arXiv:2608.01630v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves factuality but adds latency and engineering overhead at serving time. We propose RING (Retrieval-Internalized Generation), a holistic paradigm spanning both architecture and training that injects large-scale external knowledge into a extit{Mixture-of-Memory Experts} and learns parametric search over this internal memory via reinforcement learning, removing the external retriever entirely. Training proceeds in three stages: continued pre-training injects new corpora into a Knowledge Expert via our novel extit{Dual Causal Attention}; supervised fine-tuning teaches a ``search-then-answer'' pattern; and reinforcement learning with hierarchical rewards optimizes the routing-and-search policy over the parametric memory. Unlike prior parametric injection methods that pair internal memory with a fixed or rule-based retriever, RING {learns} its retrieval policy directly from task signals. We further frame RING theoretically as a search-free approximation to the classical RAG objective. To evaluate large-scale injection of genuinely {new} knowledge without test-time leakage, we further construct News-2025, a benchmark built from news strictly post-dating the base LLM's pretraining cutoff. RING matches or surpasses both search-based RAG and parametric injection baselines in accuracy and efficiency.

Related

• Generation-Augmented Generation: A Plug-and-Play Framework for Private Knowledge Injection in Large Language Models
• Domain Fine-Tuning vs. Retrieval-Augmented Generation for Medical Multiple-Choice Question Answering: A Controlled Comparison at the 4B-Parameter Scale
• RAG over Thinking Traces Can Improve Reasoning Tasks

Source: arXiv cs.CL | 2026-08-04