语言大模型 / LLM

Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects

事后诸葛亮：构建具有保留、回忆和反思能力的智能体记忆

Chris Latimer, Nicoló Boschi, Andrew Neeser, Chris Bartholomew, Gaurav Srivastava, Xuan Wang, Naren Ramakrishnan

机构 * The Washington Post（华盛顿邮报） ； Virginia Tech（弗吉尼亚理工大学） 纠错

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结 Hindsight通过结构化内存架构提升智能体在长对话中的记忆与推理能力，显著提高多会话和开放领域问题的准确率。

Exploring Automated Recognition of Instructional Activity and Discourse from Multimodal Classroom Data

探索多模态课堂数据中教学活动和话语的自动化识别

Ivo Bueno, Ruikun Hou, Babette Bühler, Tim Fütterer, James Drimalla, Jonathan Kyle Foster, Peter Youngs, Peter Gerjets, Ulrich Trautwein, Enkelejda Kasneci

专题命中 长上下文与记忆 ：language model(abstract)；prompting(abstract)

AI总结 本文通过多模态分析方法，实现了课堂活动中教学活动和话语的自动化识别，展示了微调模型在视频和 transcripts 上的高准确率，为可扩展的教师反馈系统提供了基础。

Comments This article has been accepted for publication in the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2026

Towards autonomous normative multi-agent systems for Human-AI software engineering teams

迈向自主规范的多智能体系统用于人机软件工程团队

Hoa Khanh Dam, Geeta Mahala, Rashina Hoda, Xi Zheng, Cristina Conati

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

AI总结 本文提出自主规范的多智能体系统，通过大型语言模型赋能，实现人机协作的高效软件开发。

Telco-oRAG: Optimizing Retrieval-augmented Generation for Telecom Queries via Hybrid Retrieval and Neural Routing

Telco-oRAG: 通过混合检索与神经路由优化电信查询的检索增强生成

Andrei-Laurentiu Bornea, Fadhel Ayed, Antonio De Domenico, Nicola Piovesan, Tareq Si Salem, Ali Maatouk

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

AI总结 Telco-oRAG通过混合检索与神经路由优化，提升电信领域问题回答的准确性和效率，实现开源大模型在电信基准测试中接近GPT-4水平。

Comments 12 pages, 10 figures, 4 tables

Breaking Forgetting: Training-Free Few-Shot Class-Incremental Learning via Conditional Diffusion

打破遗忘：通过条件扩散实现无训练的少样本类增量学习

Haidong Kang, Ketong Qian, Yi Lu

机构 * Northeastern University（东北大学） ； School of Information and Intelligent Science（信息与智能科学学院） ； Whiting School of Engineering（工程学院） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

AI总结 本文提出无训练的少样本类增量学习方法，通过条件扩散过程替代梯度优化，缓解灾难性遗忘并提升泛化能力。

Can We Predict the Next Question? A Collaborative Filtering Approach to Modeling User Behavior

Bokang Fu, Jiahao Wang, Xiaojing Liu, Yuli Liu

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

APVR: Hour-Level Long Video Understanding with Adaptive Pivot Visual Information Retrieval

Hong Gao, Yiming Bao, Xuezhen Tu, Bin Zhong, Linan Yue, Minling Zhang

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

Comments Accepted by AAAI 2026

Preserving Cross-Modal Consistency for CLIP-based Class-Incremental Learning

Haoran Chen, Houze Xu, Micah Goldblum, Daoguo Dong, Zuxuan Wu

机构 * Institute of Trustworthy Embodied AI（可信具身人工智能研究院） ； Fudan University（复旦大学） ； Shanghai Collaborative Innovation Center of Intelligent Visual Computing（上海智能视觉计算协同创新中心） ； Columbia University（哥伦比亚大学） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；prompting(abstract)

FengHuang: Next-Generation Memory Orchestration for AI Inferencing

Jiamin Li, Lei Qu, Tao Zhang, Grigory Chirkov, Shuotao Xu, Peng Cheng, Lidong Zhou

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization

Runpeng Geng, Yanting Wang, Chenlong Yin, Minhao Cheng, Ying Chen, Jinyuan Jia

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments The code is available at https://github.com/sleeepeer/PISanitizer

ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

Juyuan Wang, Rongchen Zhao, Wei Wei, Yufeng Wang, Mo Yu, Jie Zhou, Jin Xu, Liyan Xu

机构 * Tencent（腾讯） 纠错

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted by AAAI 2026

PanoNav: Mapless Zero-Shot Object Navigation with Panoramic Scene Parsing and Dynamic Memory

Qunchao Jin, Yilin Wu, Changhao Chen

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

Comments Accepted as a poster in AAAI 2026

Towards Realistic Project-Level Code Generation via Multi-Agent Collaboration and Semantic Architecture Modeling

Qianhui Zhao, Li Zhang, Fang Liu, Junhang Cheng, Chengru Wu, Junchen Ai, Qiaoyuanhe Meng, Lichen Zhang, Xiaoli Lian, Shubin Song, Yuanping Guo

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

Hybrid Quantum-Classical Recurrent Neural Networks

Wenduan Xu

机构 * Quantinuum Cambridge, UK（Quantinuum剑桥） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Clarified expectation-value-based readouts and made minor text edits

Higher-order Linear Attention

Yifan Zhang, Zhen Qin, Quanquan Gu

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Project Page: https://github.com/yifanzhang-pro/HLA

A Memory-Efficient Retrieval Architecture for RAG-Enabled Wearable Medical LLMs-Agents

Zhipeng Liao, Kunming Shao, Jiangnan Yu, Liang Zhao, Tim Kwang-Ting Cheng, Chi-Ying Tsui, Jie Yang, Mohamad Sawan

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

Comments Accepted by BioCAS2025

AgentFold: Long-Horizon Web Agents with Proactive Context Management

Rui Ye, Zhongwang Zhang, Kuan Li, Huifeng Yin, Zhengwei Tao, Yida Zhao, Liangcai Su, Liwen Zhang, Zile Qiao, Xinyu Wang, Pengjun Xie, Fei Huang, Siheng Chen, Jingren Zhou, Yong Jiang

机构 * Tongyi Lab（通义实验室） ； Alibaba Group（阿里巴巴集团） 纠错

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 26 pages, 9 figures

Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracy

Yunhang Shen, Chaoyou Fu, Shaoqi Dong, Xiong Wang, Yi-Fan Zhang, Peixian Chen, Mengdan Zhang, Haoyu Cao, Ke Li, Shaohui Lin, Xiawu Zheng, Yan Zhang, Yiyi Zhou, Ran He, Caifeng Shan, Rongrong Ji, Xing Sun

机构 * Tencent Youtu Lab（腾讯云图实验室） ； Nanjing University（南京大学） ； East China Normal University（华东师范大学） ； Xiamen University（厦门大学） ； CASIA（中国科学院自动化研究所） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

Comments https://github.com/VITA-MLLM/Long-VITA

A Video Is Not Worth a Thousand Words

Sam Pollard, Michael Wray

机构 * University of Bristol（布里斯托大学） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

VideoLucy: Deep Memory Backtracking for Long Video Understanding

Jialong Zuo, Yongtai Deng, Lingdong Kong, Jingkang Yang, Rui Jin, Yiwei Zhang, Nong Sang, Liang Pan, Ziwei Liu, Changxin Gao

机构 * National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（多谱段信息智能处理国家级重点实验室，人工智能与自动化学院，华中科技大学） ； NUS（国立大学新加坡） ； S-Lab, NTU（NTU的S实验室） ； Shanghai AI Lab（上海人工智能实验室） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

Comments NeurIPS-2025 Accepted Paper

FlowMoE: A Scalable Pipeline Scheduling Framework for Distributed Mixture-of-Experts Training

Yunqi Gao, Bing Hu, Mahdi Boloursaz Mashhadi, A-Long Jin, Yanfeng Zhang, Pei Xiao, Rahim Tafazolli, Merouane Debbah

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

Comments Accepted at NeurIPS 2025

Memory-Augmented Log Analysis with Phi-4-mini: Enhancing Threat Detection in Structured Security Logs

Anbi Guo, Mahfuza Farooque

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

Orchestrate, Generate, Reflect: A VLM-Based Multi-Agent Collaboration Framework for Automated Driving Policy Learning

Zengqi Peng, Yusen Xie, Yubin Wang, Rui Yang, Qifeng Chen, Jun Ma

机构 * Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou)（机器人与自主系统方向，香港科学与技术大学（广州）） ； Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（计算机科学与工程系，香港科学与技术大学） ； Cheng Kar-Shun Robotics Institute, The Hong Kong University of Science and Technology（陈家骏机器人研究所，香港科学与技术大学） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；foundation model(abstract)

VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection

Ziliang Wang, Ge Li, Jia Li, Hao Zhu, Zhi Jin

专题命中 长上下文与记忆 ：LLM(abstract)；language model(abstract)

Context-Aware Multi-Turn Visual-Textual Reasoning in LVLMs via Dynamic Memory and Adaptive Visual Guidance

Weijie Shen, Xinrui Wang, Yuanqi Nie, Apiradee Boonmee

机构 * Beihua University（白华大学） ； Kasem Bundit University（Kasem Bundit大学） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

TopoNav: Topological Graphs as a Key Enabler for Advanced Object Navigation

Peiran Liu, Qiang Zhang, Daojie Peng, Lingfeng Zhang, Yihao Qin, Hang Zhou, Jun Ma, Renjing Xu, Yiding Ji

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） ； Beijing Innovation Center of Humanoid Robotics Co., Ltd.（北京人形机器人创新中心有限公司） ； Shenzhen International Graduate School, Tsinghua University（深圳国际研究生学院，清华大学） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

Harnessing the Full Potential of RRAMs through Scalable and Distributed In-Memory Computing with Integrated Error Correction

Huynh Q. N. Vo, Md Tawsif Rahman Chowdhury, Paritosh Ramanan, Murat Yildirim, Gozde Tutuncuoglu

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

MARM: Unlocking the Future of Recommendation Systems through Memory Augmentation and Scalable Complexity

Xiao Lv, Jiangxia Cao, Shijie Guan, Xiaoyou Zhou, Zhiguang Qi, Yaqiang Zang, Ming Li, Ben Wang, Kun Gai, Guorui Zhou

专题命中 长上下文与记忆 ：LLM(abstract)；language model(abstract)

Comments CIKM 2025

Retrieval Feedback Memory Enhancement Large Model Retrieval Generation Method

Leqian Li, Dianxi Shi, Jialu Zhou, Xinyu Wei, Mingyue Yang, Songchang Jin, Shaowu Yang

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

LLMulator: Generalizable Cost Modeling for Dataflow Accelerators with Input-Adaptive Control Flow

Kaiyan Chang, Wenlong Zhu, Shengwen Liang, Huawei Li, Ying Wang

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)

Comments Accepted by MICRO (IEEE/ACM International Symposium on Microarchitecture) 2025