AI Agent

Enhancing Model Context Protocol (MCP) with Context-Aware Server Collaboration

增强模型上下文协议（MCP）的上下文感知服务器协作

Meenakshi Amulya Jayanti, X. Y. Han

机构 * University of Chicago（芝加哥大学） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；multi-agent(abstract)；分类 cs.LG、cs.SE

AI总结 本研究提出CA-MCP，通过引入共享上下文存储提升多智能体系统效率，减少LLM调用次数和响应失败频率。

Integrating Language Models for Enhanced Network State Monitoring in DRL-Based SFC Provisioning

在基于深度强化学习的SFC配置中整合语言模型以增强网络状态监控

Parisa Fard Moshiri, Murat Arda Onsu, Poonam Lohan, Burak Kantarci, Emil Janulewicz

机构 * University of Ottawa（渥太华大学） ； Ciena（Ciena公司） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；planning(abstract)；分类 cs.AI、cs.CL

AI总结 本文提出将深度强化学习与BERT结合，以提升基于DRL的SFC配置中网络状态监控的效率和准确性。

Comments 6 pages, 5 figures, submitted to 30th IEEE International Symposium on Computers and Communications (ISCC) 2025

RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction

RealMem: 在真实世界中评估大语言模型的内存驱动交互

Haonan Bian, Zhiyuan Yao, Sen Hu, Zishan Xu, Shaolei Zhang, Yifu Guo, Ziliang Yang, Xueran Han, Huacan Wang, Ronghao Chen

机构 * Xidian University（西安电子科技大学） ； Zhejiang University（浙江大学） ； Peking University（北京大学） ； Shanghai Jiao Tong University（上海交通大学） ； Renmin University of China（中国人民大学） ； Sun Yat-sen University（中山大学） ； University of the Chinese Academy of Sciences（中国科学院大学） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；multi-agent(abstract)；分类 cs.AI、cs.CL

AI总结 RealMem是一个基于真实项目场景的基准，评估大语言模型在长期项目导向交互中的记忆管理能力。

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval

MemoryGraft: 通过中毒经验检索持续破坏LLM代理

Saksham Sahai Srivastava, Haoyu He

机构 * School of Computing University of Georgia（计算机学院 佐治亚大学） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；agentic(abstract)；分类 cs.AI、cs.LG

AI总结 MemoryGraft 通过在LLM代理的长期记忆中植入恶意经验，实现对代理行为的持续破坏。

Comments 14 pages, 1 figure, includes appendix

Efficient On-Device Agents via Adaptive Context Management

通过自适应上下文管理实现高效的设备端代理

Sanidhya Vijayvargiya, Rahul Lokesh

机构 * Language Technologies Institute, Carnegie Mellon University（语言技术研究所，卡内基梅隆大学） ； Samsung Research America（三星美国研究） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；AI agent(abstract)；分类 cs.AI、cs.LG

AI总结 本文提出了一种通过自适应上下文管理实现高效设备端代理的框架，通过动态内存系统、极简序列化格式和即时模式传递机制，显著压缩上下文并提升性能。

Comments 27 pages, 5 figures

Learning to Focus: Prioritizing Informative Histories with Structured Attention Mechanisms in Partially Observable Reinforcement Learning

Daniel De Dios Allegue, Jinke He, Frans A. Oliehoek

机构 * Delft University of Technology（代尔夫特理工大学） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；planning(abstract)；分类 cs.AI、cs.LG

Comments Accepted to Embodied World Models for Decision Making (EWM) Workshop at NeurIPS 2025

Resolve Highway Conflict in Multi-Autonomous Vehicle Controls with Local State Attention

Xuan Duy Ta, Bang Giang Le, Thanh Ha Le, Viet Cuong Ta

机构 * VNU University of Engineering and Technology（越南工程大学） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；multi-agent(abstract)；分类 cs.AI、cs.LG

Long Story Generation via Knowledge Graph and Literary Theory

Ge Shi, Kaiyu Huang, Guochen Feng

机构 * Beijing Jiaotong University（北京交通大学） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；multi-agent(abstract)；分类 cs.AI、cs.CL

BCR-DRL: Behavior- and Context-aware Reward for Deep Reinforcement Learning in Human-AI Coordination

Xin Hao, Bahareh Nakisa, Mohmmad Naim Rastgoo, Gaoyang Pang

机构 * Deakin University（德肯大学） ； Monash University（莫纳什大学） ； The University of Sydney（悉尼大学） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；AI agent(abstract)；分类 cs.AI、cs.LG

Journal ref The 28th European Conference on Artificial Intelligence (ECAI 2025)

Solving Formal Math Problems by Decomposition and Iterative Reflection

Yichi Zhou, Jianqiu Zhao, Yongxin Zhang, Bohan Wang, Siran Wang, Luoxin Chen, Jiahui Wang, Haowei Chen, Allan Jie, Xinbo Zhang, Haocheng Wang, Luong Trung, Rong Ye, Phan Nhat Hoang, Huishuai Zhang, Peng Sun, Hang Li

机构 * University of science and technology of China（科学技术大学） ； Peking University（北京大学） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；agentic(abstract)；分类 cs.AI、cs.LG

Sable: a Performant, Efficient and Scalable Sequence Model for MARL

Omayma Mahjoub, Sasha Abramowitz, Ruan de Kock, Wiem Khlifi, Simon du Toit, Jemma Daniel, Louay Ben Nessir, Louise Beyers, Claude Formanek, Liam Clark, Arnu Pretorius

专题命中 记忆与上下文管理 ：agent(abstract)；multi-agent(abstract)；分类 cs.AI、cs.LG

A Finite-State Controller Based Offline Solver for Deterministic POMDPs

Alex Schutz, Yang You, Matias Mattamala, Ipek Caliskanelli, Bruno Lacerda, Nick Hawes

机构 * University of Oxford（牛津大学） ； UK Atomic Energy Authority（英国原子能局） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；planning(abstract)；分类 cs.AI、cs.LG

Comments 9 pages, 6 figures. Appendix attached. To be published in Proceedings of IJCAI 2025. For code see http://github.com/ori-goals/DetMCVI

Investigating Relational State Abstraction in Collaborative MARL

Sharlin Utke, Jeremie Houssineau, Giovanni Montana

专题命中 记忆与上下文管理 ：agent(abstract)；multi-agent(abstract)；分类 cs.AI、cs.LG

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39 No. 20 (2025), 20947-20955

Uncertainty Quantification in Continual Open-World Learning

Amanda S. Rios, Ibrahima J. Ndiour, Parual Datta, Jaroslaw Sydir, Omesh Tickoo, Nilesh Ahuja

专题命中 记忆与上下文管理 ：agent(abstract)；AI agent(abstract)；分类 cs.AI、cs.LG

Comments Manuscript Under Review (full-length); Related 4-page manuscripts accepted at Neurips 2024 Non-Archival Workshops https://sites.google.com/view/continual-fomo-workshop and https://imol-workshop.github.io/

Meta-Reflection: A Feedback-Free Reflection Learning Framework

Yaoke Wang, Yun Zhu, Xintong Bao, Wenqiao Zhang, Suyang Dai, Kehan Chen, Wenqiang Li, Gang Huang, Siliang Tang, Yueting Zhuang

专题命中 记忆与上下文管理 ：agent(abstract)；multi-agent(abstract)；分类 cs.AI、cs.CL

Machine Theory of Mind for Autonomous Cyber-Defence

Luke Swaby, Matthew Stewart, Daniel Harrold, Chris Willis, Gregory Palmer

专题命中 记忆与上下文管理 ：agent(abstract)；autonomous agent(abstract)；分类 cs.AI、cs.LG

Comments 29 pages, 17 figures, 12 tables

Out-of-Distribution Detection for Neurosymbolic Autonomous Cyber Agents

Ankita Samaddar, Nicholas Potteiger, Xenofon Koutsoukos

专题命中 记忆与上下文管理 ：agent(abstract)；autonomous agent(abstract)；分类 cs.AI、cs.LG

Comments 9 pages, 10 figures, IEEE International Conference on AI in Cybersecurity (ICAIC), 2025

Self-optimization in distributed manufacturing systems using Modular State-based Stackelberg Games

Steve Yuwono, Ahmar Kamal Hussain, Dorothea Schwung, Andreas Schwung

专题命中 记忆与上下文管理 ：agent(abstract)；multi-agent(abstract)；分类 cs.AI、cs.LG

Comments This pre-print was submitted to Journal of Manufacturing Systems on October 30, 2024

Posterior Sampling-based Online Learning for Episodic POMDPs

Dengwang Tang, Dongze Ye, Rahul Jain, Ashutosh Nayyar, Pierluigi Nuzzo

专题命中 记忆与上下文管理 ：agent(abstract)；multi-agent(abstract)；分类 cs.AI、cs.LG

Comments 41 pages, 9 figures

Gradient-based Learning in State-based Potential Games for Self-Learning Production Systems

Steve Yuwono, Marlon Löppenberg, Dorothea Schwung, Andreas Schwung

专题命中 记忆与上下文管理 ：agent(abstract)；multi-agent(abstract)；分类 cs.AI、cs.LG

A Methodology-Oriented Study of Catastrophic Forgetting in Incremental Deep Neural Networks

Ashutosh Kumar, Sonali Agarwal, D Jude Hemanth

专题命中 记忆与上下文管理 ：agent(abstract)；autonomous agent(abstract)；分类 cs.AI、cs.LG

GRSN: Gated Recurrent Spiking Neurons for POMDPs and MARL

Lang Qin, Ziming Wang, Runhao Jiang, Rui Yan, Huajin Tang

专题命中 记忆与上下文管理 ：agent(abstract)；multi-agent(abstract)；分类 cs.AI、cs.LG

VERSE: Virtual-Gradient Aware Streaming Lifelong Learning with Anytime Inference

Soumya Banerjee, Vinay K. Verma, Avideep Mukherjee, Deepak Gupta, Vinay P. Namboodiri, Piyush Rai

专题命中 记忆与上下文管理 ：agent(abstract)；AI agent(abstract)；分类 cs.AI、cs.LG

Iteratively Learn Diverse Strategies with State Distance Information

Wei Fu, Weihua Du, Jingwei Li, Sunli Chen, Jingzhao Zhang, Yi Wu

专题命中 记忆与上下文管理 ：agent(abstract)；multi-agent(abstract)；分类 cs.AI、cs.LG

Optimizing Memory Mapping Using Deep Reinforcement Learning

Pengming Wang, Mikita Sazanovich, Berkin Ilbeyi, Phitchaya Mangpo Phothilimthana, Manish Purohit, Han Yang Tay, Ngân Vũ, Miaosen Wang, Cosmin Paduraru, Edouard Leurent, Anton Zhernov, Po-Sen Huang, Julian Schrittwieser, Thomas Hubert, Robert Tung, Paula Kurylowicz, Kieran Milan, Oriol Vinyals, Daniel J. Mankowitz

专题命中 记忆与上下文管理 ：agent(abstract)；planning(abstract)；分类 cs.AI、cs.LG

Towards a Causal Probabilistic Framework for Prediction, Action-Selection & Explanations for Robot Block-Stacking Tasks

Ricardo Cannizzaro, Jonathan Routley, Lars Kunze

专题命中 记忆与上下文管理 ：agent(abstract)；autonomous agent(abstract)；分类 cs.AI、cs.LG

Comments 4 pages, 4 figures, camera-ready manuscript, accepted to the "Causality for Robotics: Answering the Question of Why" workshop at the 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation

Qiwen Cui, Kaiqing Zhang, Simon S. Du

专题命中 记忆与上下文管理 ：agent(abstract)；multi-agent(abstract)；分类 cs.AI、cs.LG

Comments 51 pages. Update: Accepted for presentation at the Conference on Learning Theory (COLT) 2023

Modeling Dynamic Environments with Scene Graph Memory

Andrey Kurenkov, Michael Lingelbach, Tanmay Agarwal, Emily Jin, Chengshu Li, Ruohan Zhang, Li Fei-Fei, Jiajun Wu, Silvio Savarese, Roberto Martín-Martín

专题命中 记忆与上下文管理 ：agent(abstract)；AI agent(abstract)；分类 cs.AI、cs.LG

Learning, Fast and Slow: A Goal-Directed Memory-Based Approach for Dynamic Environments

John Chong Min Tan, Mehul Motani

专题命中 记忆与上下文管理 ：agent(abstract)；planning(abstract)；分类 cs.AI、cs.LG

Comments 22 pages

Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning

Aviv Netanyahu, Tianmin Shu, Joshua Tenenbaum, Pulkit Agrawal

专题命中 记忆与上下文管理 ：agent(abstract)；AI agent(abstract)；分类 cs.AI、cs.LG

Comments ICML 2022, the first two authors contributed equally, project page https://www.tshu.io/GEM