← Back to all news
arXiv Machine Learning By Zhibo Hou, Fan Zhao, Zhiyu An, Wan Du

From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection

Read the original on arXiv Machine Learning →

The paper introduces Golden-GRPO Injection (GRIN), a three-stage self‑learning framework that uses a mixed‑policy reinforcement learning algorithm to inject knowledge into large language models. GRIN injects a golden answer to provide learning signals even when on‑policy rollouts fail on novel facts, and is evaluated on two new document‑level benchmarks—Blank and Counter—that test novel acquisition and counterfactual overwrite. Experiments show that mixed‑policy RL enables knowledge absorption beyond what supervised fine‑tuning can achieve, with GRIN outperforming SFT and other RL baselines on harder question types while matching them on basic fact recall.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Aug 25

DeepRefine: Agentic Knowledge Refinement via Reinforcement Learning

DeepRefine is a reinforcement learning framework that improves the quality of pre‑constructed structured knowledge bases—such as knowledge graphs or LLM‑Wikis—by engaging in multi‑turn interactions with the base. It performs abductive diagnosis to locate defects, then applies targeted refinement actions to incrementally update the knowledge base. The system uses a Gain‑Beyond‑Draft reward to train its refinement policy end‑to‑end, achieving consistent downstream performance gains over strong baselines.

By Haoyu Huang, Jiaxin Bai, Shujie Liu, Yang Wei, Huihao Jing, Hong Ting Tsang, Yisen Gao, Zhongwei Xie, Yufei Li, Yangqiu Song
llmsragagentsreinforcement-learning
More like this →
arXiv AI
Jun 16

Retrievable Gradients: Continual Post-Training Without Cumulative Weight Drift

arXiv:2606. 15734v1 Announce Type: cross Abstract: Continual post-training enables models to absorb emerging knowledge after deployment, but repeatedly updating shared parameters can accumulate weight drift, potentially causing catastrophic forgetting and degrading general capabilities.

By Weihang Su, Jiacheng Kang, Jingyan Xu, Qingyao Ai, Jianming Long, Hanwen Zhang, Bangde Du, Xinyuan Cao, Min Zhang, Yiqun Liu
rag
More like this →
arXiv AI
Jun 19

Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models

arXiv:2510. 21978v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models.

By Hoang Phan, Xianjun Yang, Yuanshun Yao, Jingyu Zhang, Shengjie Bi, Xiaocheng Tang, Madian Khabsa, Lijuan Liu, Deren Lei
llmsreinforcement-learningmultimodalbenchmarks
More like this →