论文

本文提出 KV Policy (KVP)，一种仅基于 key 与 value 向量、在预计算生成轨迹上训练的轻量级 per-head RL Agent 框架，证明学习预测未来 token 效用是自适应 KV cache 管理中强大且可扩展的范式。KV Policy (KVP), a framework of lightweight per-head RL agents trained on pre-computed generation traces using only key and value vectors, is introduced, demonstrating that learning to predict future token utility is a powerful and scalable paradigm for adaptive KV cache management.

本文提出 AgenticRAGTracer，这是首个主要由大语言模型自动构建、专为支持逐步验证而设计的 Agentic RAG 基准。AgenticRAGTracer is introduced, the first Agentic RAG benchmark that is primarily constructed automatically by large language models and designed to support step-by-step validation, and is primarily constructed automatically by large language models and designed to support step-by-step validation.

TritonForge 是一个面向自动化 Triton kernel 优化的 profiling 引导框架，融合 kernel 分析、运行时 profiling 与迭代式代码转换以简化优化流程，并为自动化 GPU 性能优化领域的未来研究奠定基础。TritonForge, a profiling-guided framework for automated Triton kernel optimization that integrates kernel analysis, runtime profiling, and iterative code transformation to streamline the optimization process and provides a foundation for future research in automated GPU performance optimization.

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.

本文首次对 vLLM 启动延迟进行了详细的性能表征，并构建了一个轻量级分析模型，能够针对给定硬件配置准确预测 vLLM 的启动延迟，为大规模推理环境中的资源规划提供了可操作的指导。This paper presents the first detailed performance characterization of vLLM startup latency and develops a lightweight analytical model that accurately predicts vLLM's startup latency for a given hardware configuration, providing actionable guidance for resource planning in large-scale inference environments.

本文将数据安全形式化为 provenance monomials 上的聚合谓词，并提出 Passant——一个无需物化 provenance 即可强制执行 DFC 策略的可移植查询重写层。This paper formalizes data safety as aggregate predicates over provenance monomials and presents Passant, a portable query rewriting layer that enforces DFC policies without materializing provenance.

本工作提出 AlphaEval，一个基于真实生产环境的基准，包含来自七家在其核心业务中部署 AI Agent 的公司的 94 个任务，覆盖六个 O*NET (Occupational Information Network) 领域；并贡献了一套从需求到基准的构建框架，将从需求到评估的完整流程标准化。This work presents AlphaEval, a production-grounded benchmark of 94 tasks sourced from seven companies deploying AI agents in their core business, spanning six O*NET (Occupational Information Network) domains, and contributes a requirement-to-benchmark construction framework that standardizes the entire pipeline from requirement to evaluation.

Continuum，一个通过为 KV cache 保留引入 TTL 机制来优化多轮 Agent 工作负载任务完成时间的服务系统，能保持多轮连续性，并降低 Agent 工作流的延迟。Continuum, a serving system to optimize job completion time for multi-turn agent workloads by introducing time-to-live mechanism for KV cache retention, preserves multi-turn continuity, and reduces delay for agentic workflows.

SarseX 模型无关、无需训练，并与 Prefix Cache 兼容，可为多轮对话、检索增强生成 (RAG) 和 Agent 工作流等常见在线服务场景提供统一支持。SarseX is model-agnostic, training-free, and compatible with Prefix Cache, and it provides unified support for common online serving scenarios including multi-round chat, retrieval-augmented generation (RAG), and agent workflows.

NetKV，一种使用该 oracle 信息的 O(|D|) 每请求贪心策略，其层级排序被证明对过时遥测数据具有鲁棒性；并证明随着上下文长度增长，忽略网络项会使仅缓存感知的调度任意次优。NetKV, the O(|D|) per-request greedy that consumes this oracle, has tier rankings that are provably robust to stale telemetry, and it is proved that ignoring the network term renders cache-aware-only scheduling arbitrarily suboptimal as context length grows.

本工作提出 LMCACHE，首个也是目前最高效的开源 KV 缓存方案，可将现代 LLM 引擎生成的 KV 缓存从 GPU 显存中提取并存储，并跨引擎和查询共享。This work presents LMCACHE, the first and so far the most efficient open-source KV caching solution, which extracts and stores KV caches generated by modern LLM engines out of the GPU memory and shares them across engines and queries.

构建了 RoboGenesis，一个基于仿真的工作流与数据引擎，可从原子技能组合配置好的实验工作流，对 rollout 进行验证与过滤，并跨支持的机器人配置导出结构化演示数据。RoboGenesis is built, a simulation-based workflow and data engine that composes configured laboratory workflows from atomic skills, validates and filters rollouts, and exports structured demonstrations across supported robot profiles.

本文提出 DashboardQA，这是首个明确设计用于评估视觉-语言 GUI Agent 对真实世界仪表板理解与交互能力的基准，结果表明交互式仪表板推理对所有受评估的 VLM 而言都是一项具有挑战性的任务。DashboardQA is introduced, the first benchmark explicitly designed to assess how vision-language GUI agents comprehend and interact with real-world dashboards, and indicates that interactive dashboard reasoning is a challenging task overall for all the VLMs evaluated.

本工作提出 12 个具体指标，从一致性、鲁棒性、可预测性和安全性四个关键维度分解 Agent 可靠性，可与传统评估互补，并提供用于分析 Agent 表现、退化与失败方式的工具。This work proposes twelve concrete metrics that decompose agent reliability along four key dimensions: consistency, robustness, predictability, and safety, which complement traditional evaluations while offering tools for reasoning about how agents perform, degrade, and fail.

本文提出一个 Agentic RAG 框架，使 LLM 能够使用逻辑表达式构建检索意图，同时将检索后端简化为基于倒排索引的系统，并表明将检索过程锚定在逻辑查询上可显著降低生成响应中的幻觉。This paper proposes an agentic RAG framework that enables LLMs to formulate retrieval intents using logical expressions while simplifying the retrieval backend to an inverted-index-based system, and shows that anchoring the retrieval process in logical queries substantially reduces hallucinations in generated responses.

本文对一个自 2026 年 3 月起持续运行的个人助理 Agent 运行时中的静默失败进行纵向研究，该系统包含约 40 个定时任务、8 个 LLM 提供商、一个工具治理代理以及一个知识库记忆层，由 4,286 个单元测试和 827 项治理检查守护。A longitudinal study of silent failures in a personal-assistant agent runtime in continuous production since March 2026, with roughly 40 scheduled jobs, 8 LLM providers, a tool-governance proxy, and a knowledge-base memory plane, defended by 4,286 unit tests and 827 governance checks is presented.

结果表明，纯视觉设置会降低准确率并增加 token 成本，因为 Agent 缺乏足够的符号化细节，需通过重复的视觉查询进行补偿；研究指向一种面向下一代编码 Agent 的实用文本与视觉混合设计。The results show that a strictly vision-only setup degrades accuracy and increases token cost, because agents lack sufficient symbolic detail and compensate with repeated visual queries, and point to a practical hybrid text-and-vision design for next-generation coding agents.

本文描述了 TensorFlow 接口及 Google 构建的该接口实现，已被用于开展研究，并在计算机科学及其他十余个领域中将机器学习系统部署至生产环境。The TensorFlow interface and an implementation of that interface that is built at Google are described, which has been used for conducting research and for deploying machine learning systems into production across more than a dozen areas of computer science and other fields.

本文指出基于 Transformer 的次二次时间模型的关键缺陷在于无法执行基于内容的推理，并将选择性 SSM 集成到不包含注意力乃至 MLP 块的简化端到端神经网络架构（Mamba）中。This work identifies that a key weakness of subquadratic-time models based on Transformer architecture is their inability to perform content-based reasoning, and integrates selective SSMs into a simplified end-to-end neural network architecture without attention or even MLP blocks (Mamba).

本文为两部分组成的专题论文，介绍物理信息神经网络——一类在训练求解监督学习任务时遵循由一般非线性偏微分方程所描述的物理定律的网络；并展示如何利用这些网络推断偏微分方程的解，以及获得对所有输入坐标和自由参数完全可微的物理信息代理模型。This two part treatise introduces physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations and demonstrates how these networks can be used to infer solutions topartial differential equations, and obtain physics-informed surrogate models that are fully differentiable with respect to all input coordinates and free parameters.

本文认为，可解释 AI 研究总体上有助于推动 AI/ML 在医疗领域的落地，并特别有助于增强透明性与信任。It is argued that research in explainable-AI would generally help to facilitate the implementation of AI/ML in the medical domain, and specifically help to facilitates transparency and trust.

本文从技术演进的角度，对这一快速发展的研究领域进行了广泛综述，跨越超过四分之一世纪的时间跨度（从 1990 年代到 2022 年）。This article extensively reviews this fast-moving research field in the light of technical evolution, spanning over a quarter-century’s time (from the 1990s to 2022).

一个能够将任意自然语言任务轻松映射为人类可读 prompt 形式的系统，并在覆盖多种任务的多任务混合数据上对预训练 encoder-decoder 模型进行微调。A system for easily mapping any natural language tasks into a human-readable prompted form and fine-tune a pretrained encoder-decoder model on this multitask mixture covering a wide variety of tasks.

对现有图神经网络模型进行了详细综述，系统性地归纳了其应用，并提出了四个有待解决的未来研究方向A detailed review over existing graph neural network models is provided, systematically categorize the applications, and four open problems for future research are proposed.

文章论证了 Transformers 可作为医学图像分割任务的强大编码器，并通过与 U-Net 结合，恢复了局部空间信息以增强更精细的细节。It is argued that Transformers can serve as strong encoders for medical image segmentation tasks, with the combination of U-Net to enhance finer details by recovering localized spatial information.

研究表明，利用变分方法最新进展的深度生成模型与近似贝叶斯推断能够带来显著提升，使生成式方法在半监督学习上极具竞争力。It is shown that deep generative models and approximate Bayesian inference exploiting recent advances in variational methods can be used to provide significant improvements, making generative approaches highly competitive for semi-supervised learning.

本工作提出一种通过引入自注意力来提取可解释句子嵌入的新模型，使用一个二维矩阵表示嵌入，其中矩阵的每一行关注句子的不同部分。A new model for extracting an interpretable sentence embedding by introducing self-attention is proposed, which uses a 2-D matrix to represent the embedding, with each row of the matrix attending on a different part of the sentence.

本工作指出，这些局部 patch 内部的注意力同样是构建高性能视觉 Transformer 的关键，并探索了一种新架构，即 Transformer iN Transformer (TNT)。It is pointed out that the attention inside these local patches are also essential for building visual transformers with high performance and a new architecture, namely, Transformer iN Transformer (TNT), is explored.

论文表明，使用 Stanford Natural Language Inference 数据集有监督训练的通用句子表示，在广泛的迁移任务上能持续优于 SkipThought vectors 等无监督方法。It is shown how universal sentence representations trained using the supervised data of the Stanford Natural Language Inference datasets can consistently outperform unsupervised methods like SkipThought vectors on a wide range of transfer tasks.

本文提出一种权重裁剪的替代方案：对 critic 相对于其输入的梯度范数施加惩罚。其性能优于标准 WGAN，能以几乎无需调参的方式稳定训练多种 GAN 架构。This work proposes an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input, which performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning.

当将监督规模扩展到 680,000 小时的多语言、多任务数据时，所得到的模型在标准 benchmark 上泛化良好，在 zero-shot transfer 设置下常可与此前全监督方法的结果相当，且无需任何微调。When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results but in a zero-shot transfer setting without the need for any fine-tuning.