论文

本文综述了 Islamic LLMs 与可信 Islamic AI 这一新兴领域，并论证了仅具备阿拉伯语流利度不足以支撑 Islamic AI，进而提出面向抗幻觉 Islamic AI 系统的研究议程。This survey reviews the emerging field of Islamic LLMs and trustworthy Islamic AI, and argues that fluency in Arabic is not sufficient for Islamic AI, with a research agenda for hallucination-resistant Islamic AI systems.

本文对近期 KV cache 优化技术进行系统综述，将其归纳为五大方向：cache eviction、cache compression、混合内存方案、新型 attention 机制与组合策略，并指出自适应多阶段优化流水线是未来研究的重要方向。This paper provides a systematic review of recent KV cache optimization techniques, organizing them into five principal directions: cache eviction, cache compression, hybrid memory solutions, novel attention mechanisms, and combination strategies, and pointing toward adaptive, multi-stage optimization pipelines as a promising direction for future research.

本文对 LLM agent 评估这一新兴领域进行了深入综述，提出一个二维分类体系，沿评估目标维度组织已有工作，为系统性评估提供框架，使研究者与从业者能够面向真实场景部署评估 LLM agent。An in-depth overview of the emerging field of LLM agent evaluation is provided, introducing a two-dimensional taxonomy that organizes existing work along evaluation objectives and provides a framework for systematic assessment, enabling researchers and practitioners to evaluate LLM agents for real-world deployment.

本文系统梳理了 Agent 系统从 pre-LLM 时代到当前 LLM 驱动架构的演进，将其划分为软件型、物理型与自适应混合型，并突出展示了其在客户服务、软件开发、制造自动化、个性化教育、金融交易和医疗等领域的应用。This paper comprehensively examines the evolution of agent systems from the pre-LLM era to current LLM-powered architectures, categorizing agent systems into software-based, physical, and adaptive hybrid systems, highlighting applications across customer service, software development, manufacturing automation, personalized education, financial trading, and healthcare.

本综述系统梳理了超越基础 Skill 创建的 Skill 演化与评估图景，将其归纳为四种范式：执行反馈、轨迹蒸馏、压缩与强化学习，并指出了构建可泛化、高效且可验证安全的 Skill 生态的开放方向。This survey systematically examines the landscape of skill evolution and evaluation beyond foundational skill creation into four distinct paradigms, spanning execution feedback, trajectory distillation, compression, and reinforcement learning, and identifies open directions for building skill ecosystems that are generalizable, efficient, and verifiably safe.

本综述界定了 CAIS 的概念，提出基于组件角色与编排策略的多维分类体系，并分析四种基础范式：Retrieval-Augmented Generation (RAG)、LLM Agents、Multimodal LLMs (MLLMs) 与 Orchestration。This survey defines the concept of CAIS, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, and analyzes four foundational paradigms: Retrieval-Augmented Generation (RAG), LLM Agents, Multimodal LLMs (MLLMs), and Orchestration.

本综述为 LLM Agent 记忆机制提出一种新的演化框架，将发展过程形式化为三个阶段：Storage（轨迹保存）、Reflection（轨迹精炼）与 Experience（轨迹抽象）。This survey proposes a novel evolutionary framework for LLM agent memory mechanisms, formalizing the development process into three stages: Storage (trajectory preservation), Reflection (trajectory refinement), and Experience (trajectory abstraction).

本文贡献了一组在架构层面具有重要意义的 MLOps 集成与部署指南（共 25 条），分为五类，并阐述其对整体系统架构的影响。This work contributes a collection of 25 architecturally significant MLOps guidelines for model integration and deployment, organized into five categories, and describes their impact on the overall system architecture.

对聚焦MLOps工具的学术文献进行系统综述，揭示其功能、范围及其旨在解决的挑战，并突出真实MLOps pipeline中各工具间互操作性的重要性。A systematic review of the academic literature focused on MLOps tools is conducted to reveal their function, scope, and the challenges they are designed to address and highlight the importance of interoperability across MLOps tools in real-world MLOps pipelines.

本文给出一份关于Agentic RAG系统的分析综述，梳理RAG范式的演进，提出基于Agent数量、控制结构、自主性与知识表示的Agentic RAG架构分类法，并对现有框架的设计权衡进行比较分析。An analytical survey of Agentic RAG systems is presented, which traces the evolution of RAG paradigms, introduces a principled taxonomy of Agentic RAG architectures based on agent cardinality, control structure, autonomy, and knowledge representation, and provides a comparative analysis of design trade-offs across existing frameworks.

提出一个全谱系的人类上下文分类法，将六个相互关联的层级整合在一起：将人类视为通过视觉外观与空间几何可观测的主体、视为通过运动学动态与交互建模的动态行动者，以及视为通过世界仿真与具身智能定位的处境化 Agent。A full-spectrum human context taxonomy is introduced that integrates six interconnected levels by viewing humans as observable subjects through visual appearance and spatial geometry, as dynamic actors through kinematic dynamics and interaction modeling, and as situated agents through world simulation and embodied agency.

本文对 LLM 推理服务方法进行了全面综述，涵盖基础的实例级方法、深入的集群级策略、新兴的场景方向以及其他重要但零散的领域。This paper provides a comprehensive survey of LLM inference serving methods, covering fundamental instance-level approaches, in-depth cluster-level strategies, emerging scenario directions, and other miscellaneous but important areas.

本文综述了 agentic artifact creation，即有状态的构建过程，其中 AI 系统实体地构造或修改交付物，且中间观察结果会重定向后续工作；并提出了若干原则，使承诺与责任显式化、将反馈转化为针对性修复，以及在变更后重新验证受影响的状态。This survey examines agentic artifact creation, which is defined as stateful construction in which an AI system materially constructs or revises a deliverable and intermediate observations redirect later work, and formulate principles for keeping commitments and responsibility explicit, turning feedback into targeted repair, and revalidating affected state after change.

本综述将崩溃视为受三处杠杆共同支配的症状：信号施加位置（即 token 加权方式）、教师所见信息（即特权信息的性质）、以及信号变化时机（即教师的动态性与引导衰减）。This review treats collapse as a symptom governed by three levers: where the signal is applied, that is, how tokens are weighted; what the teacher is shown, that is, the nature of the privileged information; and when the signal changes, that is, the teacher's dynamics and the decay of guidance.

本综述涵盖视觉与音视频 VideoLLM 的推理效率机制，这些机制报告了参数数量、每输入 FLOPs、延迟、内存或视觉/音频 token 数量的具体削减量，并按方法所作用的 pipeline 阶段加以组织。This survey covers inference-efficiency mechanisms for visual and audiovisual VideoLLMs that report concrete reductions in parameter count, FLOPs per input, latency, memory, or visual and audio token count, and organize methods by the pipeline stage at which they act.

本文聚焦 LLM 驱动的 kernel generation 领域，给出现有方法的结构化综述，涵盖 LLM-based 方法与 agentic optimization workflow，并系统梳理了支撑该领域学习与评测的数据集与 benchmark。This survey addresses the gap in LLM-driven kernel generation by providing a structured overview of existing approaches, spanning LLM-based approaches and agentic optimization workflows, and systematically organizing the datasets and benchmarks that underpin learning and evaluation in this domain.

本文探讨了 cloud platform 与 distributed system 在支撑 LLM 可扩展性、效率与优化方面的作用，涵盖数据管理、资源优化，以及对 microservices、autoscaling 与 hybrid cloud-edge 方案的需求。The role of cloud platforms and distributed systems in supporting the scalability, efficiency, and optimization of LLMs is explored, including data management, resource optimization, and the need for microservices, autoscaling, and hybrid cloud-edge solutions.

本文系统梳理了基于 LLM 的现代智能体中记忆的设计、实现与评估方法，覆盖 2022 年至 2026 年初的相关工作，并将 Agent 记忆形式化为一个涵盖时间范围、表示基底与控制策略的三维分类体系。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, and formalizes agent memory as a three-dimensional taxonomy spanning temporal scope, representational substrate, and control policy.

论文论证了物理先验提供了一种与机器人领域高度相关的归纳偏置，其作用是与数据驱动学习互补而非取代，从而为更通用、数据高效且可信的机器人系统铺平道路。It is argued that physics priors provide a particularly relevant robotics-specific inductive bias, complementing rather than replacing data-driven learning, and paving the way toward more generalizable, data-efficient, and trustworthy robotic systems.

本综述对 RAG 进行了全面考察，将其视为一个模块化且持续演进的范式，能够提升基于 LLM 系统的事实可靠性、适应性与任务对齐，并指出了持续存在的挑战。This survey presents a comprehensive examination of RAG as a modular and evolving paradigm that enhances factual reliability, adaptability, and task alignment in LLM based systems and identifies persistent challenges.

本文首次系统梳理了深度学习研究迄今为止的激活函数应用趋势，将实践中的使用情况与文献中的研究成果进行对比。This paper will be the first, to compile the trends in AF applications in practice against the research results from literature, found in deep learning research to date.

这篇综述旨在为推进可控且可靠的视频生成模型及帧后训练提供统一的框架，并基于对齐信号的施加方式区分隐式对齐与显式对齐，从而给出结构化的概念基础与实践指导。This survey aims to provide a structured conceptual foundation and practical guidance for advancing controllable and reliable video generation models and frame post-training as a unifying framework and distinguish between implicit alignment and explicit alignment based on how alignment signals are enforced.

综述了包括广泛使用的"恐惧诉求"在内的说服技巧的适用性，并提炼出意识宣传活动的基本要素以及导致活动成败的关键因素。The suitability of persuasion techniques, including the widely used 'fear appeals', are reviewed, and essential components for an awareness campaign as well as factors which can lead to a campaign's success or failure are extracted.

这是一篇综述文章，围绕机器学习技术（特别是大语言模型）展开，旨在以对数值方法领域专家友好的方式阐释 LLM 的核心概念。This is a survey article that centers on machine learning techniques, with a particular focus on large language models, to clarify the core concepts behind Large Language Models in a manner accessible to specialists in numerical methods.

LLM 越来越多地作为组件嵌入软件系统，并以 chatbot、copilot、RAG、workflow、coding agent、AI agent 等标签推广。这些标签究竟指代真实的架构形态，还是仅作品牌包装，尚未得到系统性评估。在调研的来源中，标签确实承载架构含义，在厂商用法中体现得最为清晰：copilot 指在逐步用户确认下操控宿主应用的 router-worker 架构，而近来向 agent 标签的迁移则与 AI 自主规划相吻合……Large language models (LLMs) are increasingly embedded as components in software systems, marketed under labels such as chatbot, copilot, retrieval-augmented generation, workflow, coding agent and AI agent. Whether these labels denote genuine architectural forms or serve as branding has not been assessed systematically. In the sources surveyed, labels do carry architectural content, most clearly in vendor usage: copilot denotes a router-worker architecture operating a host application under step-by-step user confirmation, while the more recent shift to the label agent coincides with AI-planned

本综述从数据中心化视角梳理 LLM 智能体的隐私问题，围绕智能体所接触的数据而非按攻击类型组织领域，并以"data agent"作为处理数据的 LLM 智能体的简称。This survey surveys the privacy of LLM agents from a data-centric view, organizing the field around the data an agent touches rather than by attack type, and uses data agent as shorthand for an LLM agent that works with data.

提出 RedVox，一个基于真实人声构建的音频与语音多语言安全性与公平性基准，涵盖五种语言中的不安全与不公平的刻板请求；研究发现漏洞即使在非对抗条件下仍然存在，在非英语语言中更为严重，且在请求来自语音输入时会被进一步放大。RedVox is introduced, a multilingual safety and fairness benchmark for audio and speech built on real voices, covering unsafe and unfair stereotypical requests across five languages, finding that vulnerabilities persist even under non-adversarial conditions, worsen in non-English languages, and are amplified when the request comes from a spoken input.

研究发现重建质量与表示质量是解耦的；在所考察的任务中，没有任何单一方法能够在所有任务上稳定取得最优表现。It is found that reconstruction and representation quality are decoupled, and no single method consistently performs best across the tasks considered here and no single method consistently performs best across the tasks considered here.

本文首次全面综述了 LLM 元认知的研究现状，涵盖用于测量和评估 LLM 元认知能力的方法与 benchmark、激发、改进与应用 LLM 元认知的技术，以及当前研究的发现与启示。The first comprehensive overview of the current state of knowledge on metacognition for LLMs is presented, including methods and benchmarks to measure and evaluate LLMs'metacognitive abilities, techniques to elicit, improve, and apply metacognition in LLMs, and findings and implications of ongoing research.

本综述将现代具备自我改进能力的 Agent 视为将经验转化为持续能力增益的自适应系统，并提出一个系统级框架，将现代 Agent 建模为由基础模型与由 prompt、memory、工具及控制逻辑构成的运行支撑层相耦合的配置。This survey frames modern self-improving agents as adaptive systems that convert experience into accumulated capability gains, and offers a system-level framework that represents a modern agent as a configuration coupling a foundation model with an operational scaffold of prompts, memory, tools, and control logic.

该综述细致梳理了 RAG 范式的演进，涵盖 Naive RAG、Advanced RAG 与 Modular RAG，并对 RAG 框架的三大基础支柱——检索、生成与增强技术——进行了深入审视。This comprehensive review paper offers a detailed examination of the progression of RAG paradigms, encompassing the Naive RAG, the Advanced RAG, and the Modular RAG, and meticulously scrutinizes the tripartite foundation of RAG frameworks, which includes the retrieval, the generation and the augmentation techniques.

该综述全面回顾了生成模型的历史与基本组件，以及 AIGC 在单模态交互与多模态交互方向的最新进展，并介绍了文本与图像生成任务及相关模型。This survey provides a comprehensive review on the history of generative models, and basic components, recent advances in AIGC from unimmodal interaction and multimodal interaction, and introduces the generation tasks and relative models of text and image.

本文旨在为研究者与从业者提供一份快速、全面的参考，通过对现有工作的广泛、信息密集型总结来汲取洞见，以推动 LLM 研究的发展。This review article is intended to provide a quick, comprehensive reference for the researchers and practitioners to draw insights from extensive, informative summaries of the existing works to advance the LLM research.