Through reinforcement learning (RL) with outcome correctness rewards, large reasoning models (LRMs) with scaled inference computation have demonstrated substantial success on complex reasoning tasks. However, the one-sided reward, focused solely on final correctness, limits its ability to provide detailed supervision over internal reasoning process. This deficiency leads to suboptimal internal reasoning quality, manifesting as issues like over-thinking, under-thinking, redundant-thinking, and disordered-thinking. Inspired by the recent progress in LRM self-rewarding, we introduce self-rewriting framework, where a model rewrites its own reasoning texts, and subsequently learns from the rewritten reasoning to improve the internal thought process quality. For algorithm design, we propose a selective rewriting approach wherein only "simple" samples, defined by the model's consistent correctness, are rewritten, thereby preserving all original reward signals of GRPO. For practical implementation, we compile rewriting and vanilla generation within one single batch, maintaining the scalability of the RL algorithm and introducing only ~10% overhead. Extensive experiments on diverse tasks with different model sizes validate the effectiveness of self-rewriting. In terms of the accuracy-length tradeoff, the self-rewriting approach achieves improved accuracy (+0.6) with substantially shorter reasoning (-46%) even without explicit instructions in rewriting prompts to reduce reasoning length, outperforming existing strong baselines. In terms of internal reasoning quality, self-rewriting achieves significantly higher scores (+7.2) under the LLM-as-a-judge metric, successfully mitigating internal reasoning flaws.
MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（北京未来区块链与隐私计算高精尖创新中心）；Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能研究院）；Beijing Academy of Blockchain and Edge Computing（北京区块链与边缘计算研究院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Models
School of Electronic and Electrical Engineering, Shanghai University of Engineering Science（上海工程技术大学电子与电气工程学院）；Tencent Youtu Lab（腾讯优图实验室）；Artificial Intelligence Innovation and Incubation Institute, Fudan University（复旦大学人工智能创新与孵化院）
Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；School of Information, Renmin University of China（中国人民大学信息学院）；Kuaishou Technology（快手科技）
Rethinking On-policy Optimization for Query Augmentation
University of Utah（犹他大学）；The University of Queensland（昆士兰大学）；University of Waterloo（滑铁卢大学）；New York University（纽约大学）；University of Notre Dame（圣母大学）；Université de Montréal（蒙特利尔大学）；Google DeepMind（谷歌DeepMind）；University of Oklahoma（俄克拉荷马大学）
Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity
School of Control and Computer Engineering, North China Electric Power University（华北电力大学控制与计算机工程学院）；Department of Computer & Information Science & Engineering, University of Florida（佛罗里达大学计算机与信息科学与工程系）；NLP2CT Lab, Department of Computer and Information Science, University of Macau（澳门大学计算机与信息科学系NLP2CT实验室）；Institute of International Language Services Studies, Macau Millennium College（澳门千禧学院国际语言服务研究所）
LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognition
School of Computer Science, Fudan University（复旦大学计算机科学学院）；School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）；Institute of Modern Languages and Linguistics, Fudan University（复旦大学现代语言与语言学研究所）
