论文

该方法通过在现有企业搜索基础设施之上叠加一层轻量级 harness，为推理型 LLM 配备 search、find、open、summarize 等工具，使其能够自主地迭代检索信息、跨文档导航并分析证据，从而降低对单一环节的过度依赖。The approach reduces this overdependence by layering a lightweight harness on top of existing enterprise search infrastructure, equipping a reasoning LLM with search, find, open, and summarize tools enabling the model to iteratively retrieve information, navigate within documents, and analyze evidence autonomously.

本文提出了一种实证方法，用于研究基于 GPU 的 LLM 推理服务系统中的 software aging 问题，并提供了一个可复现的框架，开辟了 software aging 与 software rejuvenation 与 LLM serving 交叉方向的研究。This paper proposes an empirical methodology to study software aging in GPU-based LLM serving systems and provides a reproducible framework that opens a research direction at the intersection of the software aging and rejuvenation and LLM serving communities.

分析表明，鲁棒的长期记忆（Long-Term Memory）安全无法仅在 retrieval 或执行阶段后置加固，而必须在最初就以存储阶段的溯源、版本化与策略感知的 retention 为基础进行锚定。This analysis indicates that robust Long-Term Memory security cannot be retrofitted at retrieval or execution time alone, but must be anchored in storage-time provenance, versioning, and policy-aware retention from the outset.

本文推出 STEP3-VL-10B，一个面向"紧凑效率与前沿级多模态智能"权衡的轻量级开源基础模型，并发布完整模型套件，为社区提供强大、高效且可复现的 baseline。STEP3-VL-10B is presented, a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence, and the full model suite is released to provide the community with a powerful, efficient, and reproducible baseline.

本文概述了第二届 MAGMaR（Multimodal Retrieval 驱动的多模态增强生成）研讨会共享任务的成果，参赛系统聚焦于视频检索，或在给定检索视频的基础上进行有依据的文章生成。This overview paper presents the results of the shared task for the second workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR), where participants submitted systems focused on either video retrieval or grounded generation of articles given retrieved videos.

本文提出首个将计算与 GPU 显存约束显式纳入 LLM 推理分析的排队论框架，并推导了严格的稳定性与不稳定性条件，用以判定 LLM 推理服务能否在持续到达的请求下避免队列无界增长。This paper introduces the first queueing-theoretic framework that explicitly incorporates both computation and GPU memory constraints into the analysis of LLM inference, and derives rigorous stability and instability conditions that determine whether an LLM inference service can sustain incoming demand without unbounded queue growth.

文章认为基于实体的分解能形成对原始信息更精炼的表示，并有助于降低索引与生成过程中的噪声；在端到端 QA 评测中，VectorRAG 表现优于标准 GraphRAG，且接近当前 SOTA 图方法的效果。It is argued that entity-based decomposition yields a more distilled representation of original information, and additionally serves to reduce noise in the indexing, and generation process, and on end to end QA evaluation VectorRAG performs better than standard GraphRAG and almost as good as current SOTA graph-based solutions.

提出 SIFT：Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance，离线处理文档并提取每个文档中高分注意力的细粒度位置，以两个紧凑的位向量存储这些高分位置。SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance is proposed, which processes documents offline and extracts fine-grained locations of high attention scores for each document and stores locations of high scores in the form of two compact bit vectors.

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.

本文围绕形式化框架与 Agent 生命周期，对面向 LLM-based Agent 的文本世界模型进行系统性综述，旨在整合这一快速发展的方向、厘清其设计空间，并指出未来研究的开放挑战。This work systematically review text world models for LLM-based agents, organized around a formal framework and the agent lifecycle, and aims to consolidate this rapidly developing area, clarify its design space, and highlight open challenges for future research.

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).

介绍 EvoArena 基准套件，将环境变化建模为跨终端、软件与社会领域的渐进式更新序列；并提出 EvoMem，一种基于 patch 的记忆范式，将记忆演化记录为结构化的更新历史，使 Agent 能通过记忆的变化推理环境的演化。EvoArena is introduced, a benchmark suite that models environment changes as sequences of progressive updates across terminal, software, and social domains, and EvoMem is proposed, a patch-based memory paradigm that records memory evolution as structured update histories, enabling agents to reason about environmental evolution through changes in their memory.

本文提出 Beyond Rows to Reasoning (BRTR)，一种面向电子表格理解的多模态 Agentic 框架，将单轮检索替换为迭代式工具调用循环，支持从复杂分析到结构化编辑的端到端 Excel 工作流。This work introduces Beyond Rows to Reasoning (BRTR), a multimodal agentic framework for spreadsheet understanding that replaces single-pass retrieval with an iterative tool-calling loop, supporting end-to-end Excel workflows from complex analysis to structured editing.

研究表明，机器学习在公共部门的成功，将更少依赖模型准确率的突破，而更多依赖机构能否构建出透明、可复现、可问责且受公民信任的数据基础设施。It is shown that the success of machine learning in the public sector will depend less on breakthroughs in model accuracy and more on the ability of institutions to engineer transparent, reproducible, and accountable data infrastructures that citizens can trust.

介绍 Gemini for Google (GfG)，一款面向 Google 内部软件工程生态的 Gemini 专用适配版本，涵盖从构建万亿 token 的专有数据集到采用可缓解灾难性遗忘的中段训练策略的完整过程。G Gemini for Google (GfG)}, an adaptation of Gemini specialized for Google's internal software engineering ecosystem, is introduced, from curating a trillion-token proprietary dataset to implementing a mid-training strategy that mitigates catastrophic forgetting.

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.

介绍 Albireo，一种并行推理系统：通过调度与 I/O 与计算及序列并行采样的重叠来压缩不可扩展部分，从而提高可达到的 TP 度 t，且不改变模型架构。Albireo is presented, a parallel inference system that raises the attainable TP degree t by shrinking the non-scalable portion via overlap of scheduling and I/O with compute and sequence-parallel sampling, without changing model architectures.

介绍 Corpus2Skill：离线将文档语料蒸馏为分层 Skill 目录，服务时由 LLM Agent 自顶向下导航——从全局概览逐层深入到更细粒度的摘要再到具体文档，并在分支无效时回溯。Corpus2Skill is presented, which distills a document corpus offline into a hierarchical skill directory and lets an LLM agent navigate it at serve time, drilling from a bird's-eye view through progressively finer summaries down to documents, and backtracking when a branch is unproductive.

介绍 MCP-Persona，这是首个专为评估 Agent 在真实场景、个性化 MCP 工具上的表现而设计的基准，并揭示了当前 Agent 在个性化工具使用上的显著不足，从而凸显该基准在发现并解决这些局限上的关键作用。MCP-Persona is introduced, the first benchmark specifically designed for evaluating agent performance on real-world, personalized MCP tools and demonstrates their significant struggles with personalized tool use, thereby highlighting the benchmark's crucial role in identifying and addressing these limitations.

对八款主流开源 MLOps 框架的实践使用与功能增强需求进行调查，结果显示 MLOps 框架很少被直接开箱即用，也较少集成进 GitHub Workflows，开发者更多通过其 API 在项目中实现自定义功能。Investigating the practical use and desired feature enhancements of eight popular open-source MLOps frameworks indicates that users mainly ask for enhancements to core features of the frameworks, but also better API exposure and CI/CD integration.

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.

本研究对基于RAG的系统与工具增强的LLM Agent进行系统对比，特别是在Agent仅可访问基础关键词搜索工具的条件下，评估二者的检索机制与响应质量。This study conducted a systematic comparison between RAG-based systems and tool-augmented LLM agents, specifically evaluating their retrieval mechanisms and response quality when the agent only has access to basic keyword search tools.

本文主张将这些多样化的功能统一在单一抽象与一组通用计算原语之下，使其足够强大以涵盖现有用例并支持新用例。This paper argues for unifying these diverse functionalities under a single abstraction and a common set of computational primitives, powerful enough to encompass existing use cases and to support new ones.

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.

本文提出FROAV（Framework for RAG Observation and Agent Verification），一个通过提供即插即用架构——结合可视化工作流编排、综合性评估框架与可扩展Python集成——来降低LLM Agent研究门槛的开源研究平台。FROAV (Framework for RAG Observation and Agent Verification), an open-source research platform that democratizes LLM agent research by providing a plug-and-play architecture combining visual workflow orchestration, a comprehensive evaluation framework, and extensible Python integration, is presented.

本文分析了六个公共注册表中共计67,057个服务器，识别出可导致服务器劫持与调用操控的普遍隐患，并实现了MCPInspect——一款集成前分析工具，可检测误导性的工具元数据与可利用的代码漏洞。This paper analyzes 67,057 servers across six public registries and identifies widespread conditions enabling server hijacking and invocation manipulation, and implements MCPInspect, a pre-integration analysis tool that detects misleading tool metadata and exploitable code vulnerabilities.

本文提出三种协议级原语以填补Model Context Protocol的空白：身份传递、自适应工具预算与结构化错误语义，并提出Structured Error Recovery Framework (SERF)，提供机器可读的失败语义以支持确定性的Agent自校正。Three protocol-level primitives are proposed to fill gaps in the Model Context Protocol: identity propagation, adaptive tool budgeting, and structured error semantics, and the Structured Error Recovery Framework (SERF), which provides machine-readable failure semantics that enable deterministic agent self-correction.

本文提出TSseek，一个面向分布式时间序列数据集的正则表达式驱动搜索框架，并论证传统近似技术及其索引结构因无法作用于正则表达式查询构造而不适用于此类查询。This work proposes TSseek, a regular-expression-powered search framework for distributed time series datasets, and shows that conventional approximation techniques and their index structures are ill-suited for such queries because they cannot operate on regular-expression query constructs.

研究表明矛盾解析本质上是写入时并发控制，并将缺失的契约——一个在隔离性、模式与来源维度上被证明正确的写入时正确性规范——显式化，固定了每个生产启发式都默认假设、却没有任何已部署系统显式给出的保证。It is shown that contradiction resolution is write-time concurrency control and make the missing contract explicit, a write-time correctness specification, proved sound across isolation, schema, and provenance, pinning the guarantee every production heuristic assumes but no deployed system makes explicit.

本文提出Larch，一个用于优化AI SQL查询中语义过滤器执行的框架，并给出其两种变体：Larch-A2C与Larch-Sel，二者在token使用量上均始终优于现有语义过滤器优化技术。This paper introduces Larch, a framework for optimizing the execution of semantic filters in AI SQL queries and presents two Larch variants: Larch-A2C and Larch-Sel, which always outperform existing semantic filter optimization techniques in terms of token usage.

实验表明，DataEvolver 显著提升了数据质量，相比在原始数据上训练，下游 LLM 性能平均提升 10%，凸显了 LLM 与数据迭代协同演化的新机遇。Experiments show that DataEvolver substantially improves data quality and achieves an average 10\% gain in downstream LLM performance compared with training on original data, highlighting new opportunities for the iterative co-evolution of LLMs and data.

Bespoke-Card 在传统通用估计器与学习型估计器架构之外开辟了一条新的基数估计路径，它是一个 Agent 驱动的系统，将面向特定工作负载的基数估计器合成为可执行代码。Bespoke-Card is opening a new avenue for cardinality estimation next to classical generic estimators and learned estimator architectures, an agent-driven system that synthesizes workload-specific cardinality estimators as executable code.

本研究对新兴的内存键值存储进行了全面的性能与可行性评估，突出了性能、兼容性与长期可行性（包括项目成熟度、社区支持与持续开发）之间的权衡。This study presents a comprehensive performance and viability assessment of the emerging in-memory key-value stores and highlights trade-offs between performance, compatibility, and long-term viability, including project maturity, community support, and sustained development.

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.

提出 TRUSTMARGIN，一种免训练、即插即用的仲裁层，利用模型自身的似然对两个候选进行打分，在不微调、无需外部评判或额外生成的情况下，在直接回答与 RAG 之间进行选择。TRUSTMARGIN is proposed, a training-free, plug-and-play arbitration layer that scores the two existing candidates with the model's own likelihoods and selects between Direct and RAG without fine-tuning, external judges, or additional generation.