Large Language Models (LLMs) face significant challenges in long-context processing, including quadratic computational costs, information forgetting, and the context fragmentation inherent in retrieval-augmented generation (RAG). We propose a cognitively inspired framework for efficient long-context inference based on chunk-wise compression and selective memory recall, rather than processing all raw tokens. The framework segments long inputs into chunks and encodes each chunk into compressed memory representations using a learned compressor. A gating module dynamically selects relevant memory blocks, which are then iteratively processed by a reasoning module with an evolving working memory to solve downstream tasks. The compressor and reasoner are jointly optimized via end-to-end reinforcement learning, while the gating module is trained separately as a classifier. Experimental results show that the proposed method achieves competitive accuracy on multi-hop reasoning benchmarks such as RULER-HQA, extrapolates context length from 7K to 1.75M tokens, and offers a favorable accuracy-efficiency trade-off compared to strong long-context baselines. In particular, it achieves up to a 2 times reduction in peak GPU memory usage and a 6 times inference speedup over MemAgent.
DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
University of California, Santa Barbara(加州大学圣巴巴拉分校)
研究了大规模知识图谱中的学习推理问题。更具体地说,我们描述了一种新的强化学习框架学习多跳关系路径:我们使用一个基于策略的代理与连续状态的基础上知识图谱嵌入,在KG向量空间的原因,通过采样最有前途的关系,以延长其路径。实验表明,我们提出的方法优于基于路径排序的算法和知识图谱嵌入方法在Freebase和Never-Ending Language Learning数据集上的性能。
Trustworthy and Explainable Deep Reinforcement Learning for Safe and Energy-Efficient Process Control: A Use Case in Industrial Compressed Air Systems
Fraunhofer Institute for Manufacturing Engineering and Automation IPA(弗劳恩霍夫制造工程与自动化研究所);Institute for Energy Efficiency in Production EEP, University of Stuttgart(生产能效研究所,斯图加特大学);Institute of Industrial Manufacturing and Management IFF, University of Stuttgart(工业制造与管理研究所,斯图加特大学)
Coupled Variational Reinforcement Learning for Language Model General Reasoning
Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所信息处理实验室);University of Chinese Academy of Sciences(中国科学院大学)
Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning
Case Western Reserve University, Cleveland, OH, USA(凯斯西储大学);Kean University, Union, NJ, USA(凯恩大学);The Ohio State University, Columbus, OH, USA(俄亥俄州立大学);Fudan University, Shanghai, China(复旦大学);Shanghai Artificial Intelligence Laboratory, Shanghai, China(上海人工智能实验室);The University of Hong Kong, Hong Kong, China(香港大学);North Carolina State University, Raleigh, NC, USA(北卡罗来纳州立大学)
Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models
The Hong Kong Polytechnic University(香港理工大学);Zhejiang University(浙江大学);University of Electronic Science and Technology of China(电子科技大学);Reallm Labs(Reallm 实验室);Amazon(亚马逊);The Hong Kong University of Science and Technology(香港理工大学)
TACLer: Tailored Curriculum Reinforcement Learning for Efficient Reasoning
Department of XXX, University of YYY, Location, Country(XXX系,YYY大学,地点,国家);School of ZZZ, Institute of WWW, Location, Country(ZZZ学院,WWW研究所,地点,国家);Center for Language and Cognition (CLCG), University of Groningen, The Netherlands(语言与认知中心(CLCG),格罗宁根大学,荷兰)
Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs
Virginia Tech(弗吉尼亚理工大学);Emory University(埃默里大学);KAUST(阿联酋卡塔尔大学);Georgia Tech(佐治亚理工学院);Cisco(思科系统);TAMU(德克萨斯大学奥斯汀分校);UT Southwestern Medical Center(德克萨斯西南医学中心);Eigen AI
Fishing Out Free Riders: Shapley-Based Reward Attribution for Parallel Reasoning via Reinforcement Learning
ShanghaiTech University(上海科技大学);City University of Hong Kong(香港城市大学);Peking University(北京大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Zhejiang University(浙江大学)
REARANK: Reasoning Re-ranking Agent via Reinforcement Learning
Mila - Quebec AI Institute(魁北克AI研究所);Université de Montréal(蒙特利尔大学);Fudan University(复旦大学);McGill University(麦吉尔大学);Canada CIFAR AI Chair(加拿大CIFAR人工智能 chair)
Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reports
Department of Population Health Sciences, Weill Cornell Medicine, New York, NY(人口健康科学系,韦尔·柯林斯医学中心,纽约,NY);Department of Radiology, Weill Cornell Medicine, New York, NY(放射科,韦尔·柯林斯医学中心,纽约,NY);Department of Radiology, Thomas Jefferson University, Philadelphia, PA(放射科,托马斯·杰斐逊大学,费城,PA)
Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models
Harbin Institute of Technology(哈尔滨工业大学);State Key Laboratory of Cognitive Intelligence(认知智能国家重点实验室);Tianjin Normal University(天津师范大学);Pengcheng Laboratory(鹏城实验室)
Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models
Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China(哈尔滨工业大学深圳研究院);Institute of Artificial Intelligence (TeleAI), China Telecom Corp Ltd(中国电信人工智能研究院);College of Integrated Circuits, Zhejiang University, Hangzhou, Zhejiang, China(浙江大学集成电路学院);Zhongguancun Academy, Beijing, China(中关村学院)
LoopRPT: Reinforcement Pre-Training for Looped Language Models
Harbin Institute of Technology, Harbin, China(哈尔滨工业大学);Tsinghua University, Beijing, China(清华大学);The Hong Kong University of Science and Technology, Guangzhou, China(香港科学与技术大学)