论文

本文认为 UQ 研究必须转向面向交互式 Agent 的现实场景，需要一套面向 Agent 的新原则性框架，并首次提出了能涵盖现有 UQ 设置的 Agent UQ 通用形式化方法。This paper argues that UQ research must shift to realistic settings with interactive agents, and that a new principled framework for agent UQ is needed, and presents the first general formulation of agent UQ that subsumes broad classes of existing UQ setups.

文中认为，编码 Agent 已跨越能力门槛，传统的人工 code review 已不再是软件质量流水线的必要环节。It is argued that coding agents have crossed a threshold of capability at which traditional human code review is no longer a necessary component of a software quality pipeline.

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.

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.

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.

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.

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.

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.

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.

本工作提出一种新颖的混合精度 PTQ 策略，直接最小化整个模型的全局误差传播，而非孤立地处理逐层误差，并开发了一种新颖的联合优化方法，在统一搜索空间中同时学习结构化剪枝决策与混合精度量化策略。This work proposes a novel mixed-precision PTQ strategy that directly minimizes global error propagation across the entire model, rather than isolating layer-wise errors, and develops a novel joint optimization approach that simultaneously learns structural pruning decisions and mixed-precision quantization policies within a unified search space.

本工作提出 QBugLM，一个多 Agent 框架，可自动化量子软件调试流水线，覆盖基于分类法的缺陷注入、基于 LLM 的检测与修复，直至基于仿真的验证，框架无关地支持 OpenQASM 3.0 程序。This work proposes QBugLM, a multi-agent framework that automates the quantum software debugging pipeline, from taxonomy-driven bug injection to LLM-based detection and repair, and finally to simulation-based validation, for framework-agnostic OpenQASM 3.0 programs.

本工作将 embedding 缩放作为正交于稀疏度缩放的强有力维度加以探索，并推出 LongCat-Flash-Lite，一个从零训练的 68.5B 参数、约 30 亿激活参数的模型，不仅超越参数等量级的 MoE 基线，还对同规模现有模型展现出卓越竞争力。This work explores embedding scaling as a potent, orthogonal dimension for scaling sparsity and introduces LongCat-Flash-Lite, a 68.5B parameter model with ~3B activated trained from scratch that not only surpasses parameter-equivalent MoE baselines but also exhibits exceptional competitiveness against existing models of comparable scale.

ViT-5 的设计与当代基础模型实践保持一致，可作为对 vanilla ViT 的直接替换升级方案，适用于 2020 年代中期的视觉骨干网络，并为生成建模提供更强大的骨干。With a design aligned with contemporary foundation-model practices, ViT-5 offers a simple drop-in upgrade over vanilla ViT for mid-2020s vision backbones and serves as a stronger backbone for generative modeling.

GLM-5 在真实编码任务中展现出前所未有的能力，在端到端软件工程挑战的处理上超越既有基线，并提出了新颖的异步 Agent RL 算法，进一步提升了 RL 质量。GLM-5 demonstrates unprecedented capability in real-world coding tasks, surpassing previous baselines in handling end-to-end software engineering challenges and proposing novel asynchronous agent RL algorithms that further improve RL quality.

本工作借鉴线性模型的 state space model（SSM）视角，提出三项核心方法改进并组合形成更具表达力的递推结构：源自 SSM 离散化的递推式、用于更丰富状态追踪的复数值状态更新规则，以及在不增加 decode 延迟前提下提升模型性能的多输入多输出（MIMO）建模。This work introduces three core methodological improvements inspired by the state space model (SSM) viewpoint of linear models that combine to form a more expressive recurrence derived from SSM discretization, a complex-valued state update rule that enables richer state tracking, and a multi-input, multi-output (MIMO) formulation for better model performance without increasing decode latency.

Nemotron 3 Super 是 Nemotron 3 系列中首个采用 NVFP4 进行预训练的模型，借助 LatentMoE（一种同时优化精度 per FLOP 与精度 per parameter 的新型 Mixture-of-Experts 架构），并集成 MTP 层以通过原生 speculative decoding 加速推理。Nemotron 3 Super is the first model in the Nemotron 3 family to be pre-trained in NVFP4, leverage LatentMoE, a new Mixture-of-Experts architecture that optimizes for both accuracy per FLOP and accuracy per parameter, and include MTP layers for inference acceleration through native speculative decoding.

本教程综合了推动这些汇聚方向的算法、系统与设计原则，为数据科学与数据挖掘研究者提供统一视角，涵盖将 LLM、图数据管理、图挖掘、图 ML 与 agentic 计算融合到下一代 graph-native AI 系统中。This tutorial synthesizes the algorithms, systems, and design principles driving these converging directions, offering data science and data mining researchers a unified perspective on integrating LLMs, graph data management, graph mining, graph ML, and agentic computation into next-generation graph-native AI systems.

本文提出 LoRAFusion，一种面向 LLM 的高效 LoRA 微调系统，可消除不必要的内存访问，在不付出重算或同步代价的前提下保持 compute-bound GEMM 的性能，并引入面向多任务微调的自适应批处理算法。LoRAFusion is introduced, an efficient LoRA fine-tuning system for LLMs that eliminates unnecessary memory accesses and preserves the performance of compute-bound GEMMs without incurring the cost of recomputation or synchronization and introduces an adaptive batching algorithm for multi-job fine-tuning.

本文认为，AI agent——即以大语言模型作为主要推理引擎、动态生成与丢弃代码作为工具性资源的系统——的出现构成了对"软件"本身的根本性重构，而非渐进式的工具改进。This paper argues that the emergence of AI agents -- systems where large language models serve as the primary reasoning engine, dynamically generating and discarding code as an instrumental resource -- constitutes a fundamental restructuring of what software is, not an incremental tool improvement.

本文提出 MatryoshkaLoRA，一种受 Matryoshka 启发、面向 LoRA 的通用训练框架，通过在已有 LoRA adapter 之间插入一个固定的、经精心设计的对角矩阵来按比例缩放其子秩，从而学习到准确的层次化低秩表示。MatryoshkaLoRA is proposed, a general, Matryoshka-inspired training framework for LoRA that learns accurate hierarchical low-rank representations by inserting a fixed, carefully crafted diagonal matrix between the existing LoRA adapters to scale their sub-ranks accordingly.

Tutti 是一种高效的 SSD-backed KV caching 方案，将 CPU 从 HBM 与 SSD 之间的关键数据与 I/O 控制路径中彻底移除，在提供近乎无限容量的同时，实现了与 DRAM-backed LMCache 几乎相当的 inference 性能。Tutti is an efficient SSD-backed KV caching solution that eliminates CPU intervention from the critical data and I/O control paths between HBM and SSDs, and achieves nearly the same inference performance as DRAM-backed LMCache, while providing almost infinite capacity.

这些结果表明，Kueue、DAS 与 GAIE 等互补组件构成了一个高性能的协同平台，证明了 Kubernetes 能够作为承载高要求 GenAI 工作负载的统一底座。These findings illustrate that these complementary components (Kueue, DAS, and GAIE) form a cohesive, high-performance platform, proving Kubernetes' capability to serve as a unified foundation for demanding GenAI workloads.

本文提出了一种简单的 flow-control 框架，通过控制 prompt 加入 LLM 活跃集合的速率，实现更高的 token 与 request 吞吐量、更低的平均与尾部 latency，以及更稳定的 KV cache 利用率。A simple flow-control framework is proposed that controls the rate at which prompts join the active set in large language models and achieves higher token and request throughput, lower average and tail latency, and more stable KV cache utilization.

本文在 Argonne Leadership Computing Facility 的 Polaris 超级计算机上对分布式向量数据库性能进行了实证研究，选取 Qdrant 评估在最多 32 个 worker 下的插入、索引构建与 query latency。This work presents an empirical study of distributed vector database performance on the Polaris supercomputer in the Argonne Leadership Computing Facility, and selects Qdrant to evaluate insertion, index construction, and query latency with up to 32 workers.

本文提出 DualPath，一种 inference 系统，通过引入 dual-path KV-Cache loading 打破瓶颈，并实现一条新的 storage-to-decode 路径：KV-Cache 先加载到 decode engine，再通过 compute network 上的 RDMA 高效转发至 prefill engine。DualPath is presented, an inference system that breaks this bottleneck by introducing dual-path KV-Cache loading and enables a novel storage-to-decode path, in which the KV-Cache is loaded into decoding engines and then efficiently transferred to prefill engines via RDMA over the compute network.

本文通过大规模超参数搜索，系统地重新评估了 Vanilla LoRA 以及九个代表性 LoRA 变体，发现不同 LoRA 方法偏好的学习率区间各异，并将最优学习率区间的差异归因于最大 Hessian 特征值的变化，与经典学习理论相吻合。This work systematically re-evaluate nine representative LoRA variants alongside vanilla LoRA through extensive hyperparameter searches, finding that different LoRA methods favor distinct learning rate ranges and attributes the differing optimal learning rate ranges to variations in the largest Hessian eigenvalue, aligning with classical learning theories.

本文探讨容器化、微服务、动态调度等 Cloud Native 技术如何从根本上提升 LLM 推理服务，并展示 Cloud Native 系统在高需求场景下实现更高效资源分配、降低延迟与提升吞吐的能力。This article explores how Cloud Native technologies, such as containerization, microservices, and dynamic scheduling, can fundamentally improve LLM inference serving and demonstrates how a Cloud Native system enables more efficient resource allocation, reduces latency, and enhances throughput in high-demand scenarios.