语言大模型 / LLM - arXivDaily 专题

2510.07925 2025-10-10 cs.AI cs.HC 85%

Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles

Rebecca Westhäußer, Wolfgang Minker, Sebatian Zepf

机构 * Ulm University（乌尔姆大学）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 8 pages, 1 figure, 1 table

2508.14053 2025-10-10 cs.AR cs.AI cs.MA 85%

MAHL: Multi-Agent LLM-Guided Hierarchical Chiplet Design with Adaptive Debugging

Jinwei Tang, Jiayin Qin, Nuo Xu, Pragnya Sudershan Nalla, Yu Cao, Yang, Zhao, Caiwen Ding

机构 * University of Minnesota - Twin Cities（明尼苏达大学-双城分校）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2510.05186 2025-10-08 cs.DC cs.AI math.OC 85%

OptPipe: Memory- and Scheduling-Optimized Pipeline Parallelism for LLM Training

Hongpei Li, Han Zhang, Huikang Liu, Dongdong Ge, Yinyu Ye

机构 * Shanghai University of Finance and Economics（上海金融学院）； National University of Singapore（新加坡国立大学）； Shanghai Jiao Tong University（上海交通大学）； Stanford University（斯坦福大学）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Use Mathematical Programming to model Pipeline Parallelism with Offloading to balance efficiency and memory requirement

2510.02373 2025-10-06 cs.CR cs.AI 85%

A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory

Qianshan Wei, Tengchao Yang, Yaochen Wang, Xinfeng Li, Lijun Li, Zhenfei Yin, Yi Zhan, Thorsten Holz, Zhiqiang Lin, XiaoFeng Wang

机构 * Nanyang Technological University（南洋理工大学）； University of Oxford（牛津大学）； Max Planck Institute（马克斯·普朗克研究所）； The Ohio State University（俄亥俄州立大学）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2509.25370 2025-10-01 cs.AI 85%

Where LLM Agents Fail and How They can Learn From Failures

Kunlun Zhu, Zijia Liu, Bingxuan Li, Muxin Tian, Yingxuan Yang, Jiaxun Zhang, Pengrui Han, Qipeng Xie, Fuyang Cui, Weijia Zhang, Xiaoteng Ma, Xiaodong Yu, Gowtham Ramesh, Jialian Wu, Zicheng Liu, Pan Lu, James Zou, Jiaxuan You

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2509.23113 2025-09-30 cs.AI cs.CY 85%

Exploring LLM-based Frameworks for Fault Diagnosis

Xian Yeow Lee, Lasitha Vidyaratne, Ahmed Farahat, Chetan Gupta

机构 * Hitachi America Ltd.（日立美国有限公司）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2505.09081 2025-09-30 cs.SI cs.AI cs.MA 85%

SALM: A Multi-Agent Framework for Language Model-Driven Social Network Simulation

Gaurav Koley

机构 * Boston University（波士顿大学）

专题命中长上下文与记忆：language model(title,abstract)；LLM(abstract)；prompting(abstract)；分类 cs.AI

2509.21224 2025-09-26 cs.AI 85%

What Do LLM Agents Do When Left Alone? Evidence of Spontaneous Meta-Cognitive Patterns

Stefan Szeider

机构 * Algorithms and Complexity Group TU Wien（算法与复杂性组维也纳技术大学）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2507.09790 2025-09-24 cs.SE cs.AI cs.PF 85%

Prompting for Performance: Exploring LLMs for Configuring Software

Helge Spieker, Théo Matricon, Nassim Belmecheri, Jørn Eirik Betten, Gauthier Le Bartz Lyan, Heraldo Borges, Quentin Mazouni, Dennis Gross, Arnaud Gotlieb, Mathieu Acher

机构 * Inria-Simula associate team RIPOST（Inria-Simula联合团队RIPOST）； Inria Défi LLM4Code project（Inria LLM4Code项目）

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

Comments ICTAI 2025

2509.12810 2025-09-17 cs.AI 85%

H$^2$R: Hierarchical Hindsight Reflection for Multi-Task LLM Agents

Shicheng Ye, Chao Yu, Kaiqiang Ke, Chengdong Xu, Yinqi Wei

机构 * Sun Yat-sen University（中山大学）； The University of Sydney（悉尼大学）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2508.13231 2025-09-16 cs.AR cs.AI cs.PF 85%

Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System

Yunhua Fang, Rui Xie, Asad Ul Haq, Linsen Ma, Kaoutar El Maghraoui, Naigang Wang, Meng Wang, Liu Liu, Tong Zhang

机构 * Rensselaer Polytechnic Institute（拉特格斯理工学院）； IBM T.J. Watson Research Center（IBM 沃森研究中心）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments IEEE Computer Architecture Letter

2509.08596 2025-09-11 cs.CL 85%

LLM Ensemble for RAG: Role of Context Length in Zero-Shot Question Answering for BioASQ Challenge

Dima Galat, Diego Molla-Aliod

机构 * University of Technology Sydney (UTS), Australia（悉尼技术大学（UTS））

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments CEUR-WS, CLEF2025

2509.03990 2025-09-09 cs.AI 85%

Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent

Chunlong Wu, Ye Luo, Zhibo Qu, Min Wang

机构 * Tongji University（同济大学）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2506.10491 2025-09-03 cs.CL 85%

Surface Fairness, Deep Bias: A Comparative Study of Bias in Language Models

Aleksandra Sorokovikova, Pavel Chizhov, Iuliia Eremenko, Ivan P. Yamshchikov

机构 * Constructor University（Constructor大学）； CAIRO, THWS, Würzburg（CAIRO、THWS、弗赖堡）； University of Kassel（卡塞尔大学）

专题命中长上下文与记忆：language model(title,abstract)；LLM(abstract)；large language model(abstract)；分类 cs.CL

2505.20231 2025-08-14 cs.CL 85%

MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents

Yiming Du, Bingbing Wang, Yang He, Bin Liang, Baojun Wang, Zhongyang Li, Lin Gui, Jeff Z. Pan, Ruifeng Xu, Kam-Fai Wong

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2412.02252 2025-08-05 cs.CL 85%

Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity

Da Ma, Lu Chen, Situo Zhang, Yuxun Miao, Su Zhu, Zhi Chen, Hongshen Xu, Hanqi Li, Shuai Fan, Lei Pan, Kai Yu

专题命中长上下文与记忆：LLM(title)；large language model(abstract)；language model(abstract)；post-training(abstract)

Comments 14 pages, 7 figures, 7 tables

2503.21760 2025-08-04 cs.CL 85%

MemInsight: Autonomous Memory Augmentation for LLM Agents

Rana Salama, Jason Cai, Michelle Yuan, Anna Currey, Monica Sunkara, Yi Zhang, Yassine Benajiba

机构 * AWS AI（AWS人工智能）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2507.21428 2025-07-30 cs.CL 85%

MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversations

Elias Lumer, Anmol Gulati, Vamse Kumar Subbiah, Pradeep Honaganahalli Basavaraju, James A. Burke

机构 * Commercial Technology and Innovation Office, PricewaterhouseCoopers（普华永道商业技术与创新办公室）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 23 Pages, 20 Figures

2507.03153 2025-07-08 cs.LG 85%

HGCA: Hybrid GPU-CPU Attention for Long Context LLM Inference

Weishu Deng, Yujie Yang, Peiran Du, Lingfeng Xiang, Zhen Lin, Chen Zhong, Song Jiang, Hui Lu, Jia Rao

机构 * The University of Texas at Arlington（德克萨斯大学阿灵顿分校）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

2501.12372 2025-06-12 cs.DB cs.AI 85%

Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQL

Yeounoh Chung, Gaurav T. Kakkar, Yu Gan, Brenton Milne, Fatma Ozcan

机构 * Google（谷歌）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 13 pages, 6 figures, VLDB 2025

2502.14254 2025-06-12 cs.RO cs.AI 85%

Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation

Lingfeng Zhang, Yuecheng Liu, Zhanguang Zhang, Matin Aghaei, Yaochen Hu, Hongjian Gu, Mohammad Ali Alomrani, David Gamaliel Arcos Bravo, Raika Karimi, Atia Hamidizadeh, Haoping Xu, Guowei Huang, Zhanpeng Zhang, Tongtong Cao, Weichao Qiu, Xingyue Quan, Jianye Hao, Yuzheng Zhuang, Yingxue Zhang

专题命中长上下文与记忆：language model(title,abstract)；LLM(abstract)；large language model(abstract)；分类 cs.AI

2502.13172 2025-06-04 cs.CR cs.AI 85%

Unveiling Privacy Risks in LLM Agent Memory

Bo Wang, Weiyi He, Shenglai Zeng, Zhen Xiang, Yue Xing, Jiliang Tang, Pengfei He

机构 * Michigan State University（密歇根州立大学）； University of Georgia（佐治亚大学）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments ACL 2025 (Main Conference)

2505.11942 2025-06-02 cs.AI 85%

LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners

Junhao Zheng, Xidi Cai, Qiuke Li, Duzhen Zhang, ZhongZhi Li, Yingying Zhang, Le Song, Qianli Ma

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Project Page: https://caixd-220529.github.io/LifelongAgentBench/

2505.23844 2025-06-02 cs.CL 85%

Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation

Zhenglun Kong, Zheng Zhan, Shiyue Hou, Yifan Gong, Xin Meng, Pengwei Sui, Peiyan Dong, Xuan Shen, Zifeng Wang, Pu Zhao, Hao Tang, Stratis Ioannidis, Yanzhi Wang

机构 * Northeastern University（东北大学）； Peking University（北京大学）； Harvard University（哈佛大学）； Google（谷歌）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2504.00587 2025-06-02 cs.MA cs.CL 85%

AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems

Yingxuan Yang, Huacan Chai, Shuai Shao, Yuanyi Song, Siyuan Qi, Renting Rui, Weinan Zhang

机构 * Shanghai Jiao Tong University（上海交通大学）； SII

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2505.13528 2025-05-21 cs.IR cs.AI 85%

LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systems

Shengkang Gu, Jiahao Liu, Dongsheng Li, Guangping Zhang, Mingzhe Han, Hansu Gu, Peng Zhang, Ning Gu, Li Shang, Tun Lu

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 11 pages, under review

2407.04363 2025-05-16 cs.AI 85%

AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents

Petr Anokhin, Nikita Semenov, Artyom Sorokin, Dmitry Evseev, Andrey Kravchenko, Mikhail Burtsev, Evgeny Burnaev

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Code for this work is avaliable at https://github.com/AIRI-Institute/AriGraph

2505.02099 2025-05-06 cs.AI 85%

MemEngine: A Unified and Modular Library for Developing Advanced Memory of LLM-based Agents

Zeyu Zhang, Quanyu Dai, Xu Chen, Rui Li, Zhongyang Li, Zhenhua Dong

机构 * Renmin University of China（中国人民大学）； Huawei Noah’s Ark Lab（华为诺亚实验室）； Huawei Technologies Ltd.（华为技术有限公司）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Just accepted by TheWebConf'25 Resource Track

2504.17967 2025-04-28 cs.AI 85%

LLM Agent Swarm for Hypothesis-Driven Drug Discovery

Kevin Song, Andrew Trotter, Jake Y. Chen

机构 * Systems Pharmacology AI Research Center, The University of Alabama at Birmingham（系统药理学人工智能研究中心，阿拉巴马大学伯明翰分校）； Department of Biomedical Engineering, The University of Alabama at Birmingham（生物医学工程系，阿拉巴马大学伯明翰分校）

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 15 pages, 3 figures

2504.13928 2025-04-22 cs.HC cs.AI 85%

LLM-Driven NPCs: Cross-Platform Dialogue System for Games and Social Platforms

Li Song

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

1. 长上下文与记忆 4760 篇

Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles

MAHL: Multi-Agent LLM-Guided Hierarchical Chiplet Design with Adaptive Debugging

OptPipe: Memory- and Scheduling-Optimized Pipeline Parallelism for LLM Training

A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory

Where LLM Agents Fail and How They can Learn From Failures

Exploring LLM-based Frameworks for Fault Diagnosis

SALM: A Multi-Agent Framework for Language Model-Driven Social Network Simulation

What Do LLM Agents Do When Left Alone? Evidence of Spontaneous Meta-Cognitive Patterns

Prompting for Performance: Exploring LLMs for Configuring Software

H$^2$R: Hierarchical Hindsight Reflection for Multi-Task LLM Agents

Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System

LLM Ensemble for RAG: Role of Context Length in Zero-Shot Question Answering for BioASQ Challenge

Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent

Surface Fairness, Deep Bias: A Comparative Study of Bias in Language Models

MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents

Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity

MemInsight: Autonomous Memory Augmentation for LLM Agents

MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversations

HGCA: Hybrid GPU-CPU Attention for Long Context LLM Inference

Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQL

Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation

Unveiling Privacy Risks in LLM Agent Memory

LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners

Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation

AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems

LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systems

AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents

MemEngine: A Unified and Modular Library for Developing Advanced Memory of LLM-based Agents

LLM Agent Swarm for Hypothesis-Driven Drug Discovery

LLM-Driven NPCs: Cross-Platform Dialogue System for Games and Social Platforms