{"slug": "from-memorization-to-absorption-mixed-policy-rl-for-continual-knowledge", "title": "From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection", "summary": "Researchers propose Golden-GRPO Injection (GRIN), a three-stage mixed-policy reinforcement learning framework for continual knowledge injection in large language models, which outperforms supervised fine-tuning on harder question types while matching it on basic fact recall. The framework introduces Golden-GRPO, a mixed-policy RL algorithm that injects a golden answer to provide learning signal even when on-policy rollouts fail, and two document-level benchmarks, Blank and Counter, targeting novel acquisition and counterfactual overwrite. The findings establish that mixed-policy RL enables knowledge absorption beyond what supervised fine-tuning can achieve.", "body_md": "arXiv:2608.25243v1 Announce Type: new\nAbstract: Continual knowledge injection is essential for keeping large language models up-to-date in a fast-evolving world. Existing methods rely on supervised fine-tuning (SFT), which memorizes injected facts in their training format but fails to generalize across paraphrasing, document combinations, and reasoning. To address this, we propose Golden-GRPO Injection (GRIN), a three-stage self-learning framework for continual knowledge injection. Golden-GRPO is a mixed-policy reinforcement learning algorithm designed specifically for knowledge injection, which injects a golden answer to provide learning signal even when on-policy rollouts fail on novel facts. We further introduce Blank and Counter, two document-level benchmarks targeting novel acquisition and counterfactual overwrite respectively, each evaluating single-fact recall, multi-source retrieval, and inferential reasoning. Our experiments establish a clear empirical claim: mixed-policy reinforcement learning enables knowledge absorption beyond what supervised fine-tuning can achieve. GRIN substantially outperforms SFT and mixed-policy RL baselines on the harder question types while matching them on basic fact recall.", "url": "https://wpnews.pro/news/from-memorization-to-absorption-mixed-policy-rl-for-continual-knowledge", "canonical_source": "https://arxiv.org/abs/2608.25243", "published_at": "2026-08-27 04:00:00+00:00", "updated_at": "2026-08-27 04:20:29.054976+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-research"], "entities": ["arXiv", "Golden-GRPO Injection (GRIN)", "Golden-GRPO", "Blank", "Counter"], "alternates": {"html": "https://wpnews.pro/news/from-memorization-to-absorption-mixed-policy-rl-for-continual-knowledge", "markdown": "https://wpnews.pro/news/from-memorization-to-absorption-mixed-policy-rl-for-continual-knowledge.md", "text": "https://wpnews.pro/news/from-memorization-to-absorption-mixed-policy-rl-for-continual-knowledge.txt", "jsonld": "https://wpnews.pro/news/from-memorization-to-absorption-mixed-policy-rl-for-continual-knowledge.jsonld"}}