Large language model (LLM) agents increasingly operate in settings where a single context window is far too small to capture what has happened, what was learned, and what should not be repeated. Memory -- the ability to persist, organize, and selectively recall information across interactions -- is what turns a stateless text generator into a genuinely adaptive agent. This survey offers a structured account of how memory is designed, implemented, and evaluated in modern LLM-based agents, covering work from 2022 through early 2026. We formalize agent memory as a \emph{write--manage--read} loop tightly coupled with perception and action, then introduce a three-dimensional taxonomy spanning temporal scope, representational substrate, and control policy. Five mechanism families are examined in depth: context-resident compression, retrieval-augmented stores, reflective self-improvement, hierarchical virtual context, and policy-learned management. On the evaluation side, we trace the shift from static recall benchmarks to multi-session agentic tests that interleave memory with decision-making, analyzing four recent benchmarks that expose stubborn gaps in current systems. We also survey applications where memory is the differentiating factor -- personal assistants, coding agents, open-world games, scientific reasoning, and multi-agent teamwork -- and address the engineering realities of write-path filtering, contradiction handling, latency budgets, and privacy governance. The paper closes with open challenges: continual consolidation, causally grounded retrieval, trustworthy reflection, learned forgetting, and multimodal embodied memory.
Generative AI for Autonomous Driving: Frontiers and Opportunities
Texas A&M University(德克萨斯农工大学);University of California, Riverside(加州大学河滨分校);University of Michigan(密歇根大学);Purdue University(普渡大学);Columbia University(哥伦比亚大学);University of Florida(佛罗里达大学);Technische Universität München(慕尼黑技术大学);University of Wisconsin-Madison(威斯康星大学麦迪逊分校);University of Texas at Austin(德克萨斯大学奥斯汀分校);University of Notre Dame(诺特丹大学);Adobe Research(Adobe研究);Lehigh University(莱斯利大学);Cleveland State University(克利夫兰州立大学);Johns Hopkins University(约翰霍普金斯大学);University of California, Merced(加州大学默塞德分校);University of Utah(犹他大学);Texas A&M Transportation Institute(德克萨斯农工大学交通研究所);Bosch Research North America(博世北美研究);Bosch Center for Artificial Intelligence (BCAI)(博世人工智能中心);University of California, Berkeley(加州大学伯克利分校);Stanford University(斯坦福大学);NVIDIA(英伟达);Arizona State University(亚利桑那州立大学)
A Survey of Data Agents: Emerging Paradigm or Overstated Hype?
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Shanghai Jiao Tong University(上海交通大学);Renmin University of China(中国人民大学);Beijing Institute of Technology(北京理工大学);Southeast University(东南大学);Tsinghua University(清华大学);Huawei(华为);DeepWisdom
Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks
University of California, Berkeley(加州大学伯克利分校);Stanford University(斯坦福大学);Georgia Institute of Technology(佐治亚理工学院);Mohamed Bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);McGill University(麦吉尔大学);Mila(米拉研究所)
Advancing the Scientific Frontier with Increasingly Autonomous Systems
NASA Jet Propulsion Laboratory(美国国家航空航天局喷气推进实验室);University of California, Berkeley(加州大学伯克利分校);NASA Ames Research Center(美国国家航空航天局艾姆斯研究中心);Okean Solutions(Okean Solutions公司);NASA Goddard Space Flight Center(美国国家航空航天局戈达德太空飞行中心);Johns Hopkins University Applied Physics Laboratory(约翰斯·霍普金斯大学应用物理实验室);Southwest Research Institute(西南研究院);Arizona State University(亚利桑那州立大学)
Frontier AI Regulation: Managing Emerging Risks to Public Safety
Centre for the Governance of AI(人工智能治理中心);Center for a New American Security(新美国安全中心);Google DeepMind(谷歌DeepMind);Brookings Institution(布鲁金斯学会);University of Virginia(弗吉尼亚大学);OpenAI;Centre for Long-Term Resilience(长期韧性中心);Centre for the Study of Existential Risk, University of Cambridge(剑桥大学存在风险研究中心);University of Washington(华盛顿大学);Convergence Analysis;Centre for International Governance Innovation(国际治理创新中心);The Andrew W. Marshall Foundation(安德鲁·W·马歇尔基金会);Edmond & Lily Safra Center for Ethics(埃德蒙与莉莉·萨弗拉伦理中心);Harvard University(哈佛大学);University of Toronto(多伦多大学);Schwartz Reisman Institute for Technology and Society(施瓦茨·赖斯曼技术与社会研究所);Vector Institute(向量研究所);Akin Gump Strauss Hauer & Feld LLP(艾金·岗波律师事务所);Cohere For AI;Microsoft(微软);Collective Intelligence Project(集体智能项目);University of California: Los Angeles(加利福尼亚大学洛杉矶分校)
Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Survey
Hubei University(湖北大学)
自2004年DARPA Grand Challenge以来,自动驾驶技术已经经历了近二十年的快速发展。特别是近年来,随着新型传感器和深度学习技术的应用向自动驾驶领域延伸,自动驾驶技术的发展不断取得突破。因此,许多汽车制造商和高科技巨头致力于自动驾驶的研究和系统开发。然而,作为自动驾驶的基础,深度学习技术面临着许多新的安全风险。学术界针对对抗性示例和AI后门提出了深度学习对策,并将其引入自动驾驶领域进行验证。深度学习安全关系到自动驾驶系统的安全,进而关系到人身安全,是一个值得关注和研究的问题,本文综述了自动驾驶中深度学习安全技术的概念、发展和最新研究。首先,我们简要介绍了自动驾驶系统中的深度学习框架和流水线,主要包括该领域常用的深度学习技术和算法。此外,我们还重点分析了基于深度学习的自动驾驶系统在各个功能层中的潜在安全威胁。本文回顾了自动驾驶领域深度学习攻击技术的发展历程,分析了当前自动驾驶领域的最新算法,揭示了其潜在的风险。最后,我们对自动驾驶领域的深度学习安全性进行了展望,并为构建安全可信的自动驾驶系统提出了建议。
AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering
School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院);School of Artificial Intelligence, Shanghai Jiao Tong University(上海交通大学人工智能学院)
The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?
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);Ant Group(蚂蚁集团)
Large Multimodal Models for Embodied Intelligent Driving: Enabling the Next Generation of Autonomous Mobility
School of Information and Electrical Engineering, Hebei University of Engineering(河北工程大学信息与电子工程学院);School of Information Science and Engineering, Lanzhou University(兰州大学信息科学与工程学院);Department of Electrical and Computer Engineering, Auburn University(阿肯色大学电气与计算机工程系);Department of Electrical and Computer Engineering, University of Houston(休斯顿大学电气与计算机工程系);Department of Computer Science and Engineering, Kyung Hee University(庆熙大学计算机科学与工程系);Machine Learning Department, Mohamed Bin Zayed University of Artificial Intelligence(Mohamed Bin Zayed人工智能大学机器学习系)
Frontier Coding Agents Can Now Implement an AlphaZero Self-Play Machine Learning Pipeline For Connect Four That Performs Comparably to an External Solver
Department of Computer Science(计算机科学系);University of Chicago(芝加哥大学);Independent Researcher(独立研究员)
本文提出一个基准测试,评估前沿编码代理自主实现AlphaZero式机器学习流水线的能力,通过简洁任务描述而非完整前序工作参考,评估连接四游戏AI性能,发现Claude Opus 4.7在七次试验中胜过Pons求解器,其他代理表现欠佳。