2026-10论文中文摘要
选择长视界轨迹以实现可靠高效的终端智能体训练
Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training
arXiv 2610.05831 · 2026-10-06智能体排行榜的测量优先审计：污染敏感性、匹配对照再评估与评分器验证
Measurement-First Auditing of Agentic Leaderboards: Contamination Susceptibility, Matched-Control Re-evaluation, and Scorer Validation
arXiv 2610.05830 · 2026-10-06具有正则矩增长的混沌的矩估计
Moment estimates for chaoses with regular moment growth
arXiv 2610.05829 · 2026-10-06气候科学中因果推断的时空随机干预
Spatio-Temporal Stochastic Interventions for Causal Inference in Climate Science
arXiv 2610.05827 · 2026-10-06有界临时可见性：控制持续摄入的RAG向量存储中的投毒暴露
Bounded Provisional Visibility: Controlling Poisoning Exposure in Continuously Ingested RAG Vector Stores
arXiv 2610.05826 · 2026-10-06分位数感知扩散建模对高度不平衡表格数据的有用性
Usefulness of Quantile-Aware Diffusion Modeling for Highly Imbalanced Tabular Data
arXiv 2610.05825 · 2026-10-06Wentzell 算子在微分形式上的作用
The Wentzell operator on differential forms
arXiv 2610.05824 · 2026-10-06个人AI助手收益的归属：语言模型市场模拟中的卖方适应与无助手群体
Who Keeps the Gains from Personal AI Assistants? Seller Adaptation and the Unassisted in a Language-Model Market Simulation
arXiv 2610.05823 · 2026-10-06支持夫妻日常生活中的社会福祉：与同居夫妻的需求评估与协同设计
Supporting Couples' Social Well-being in Daily Life: A Needs Assessment and Co-design with Co-located Couples
arXiv 2610.05822 · 2026-10-06向量不变形式的可压缩欧拉方程的熵稳定与良好平衡间断伽辽金方法
Entropy-Stable and Well-Balanced Discontinuous Galerkin Methods for the Compressible Euler Equations in Vector-Invariant Form
arXiv 2610.05820 · 2026-10-06通过多目标强化学习实现四足机器人运输无固定堆叠载荷
Transporting Unsecured Stacked Payloads with a Quadrupedal Robot via Multi-Objective Reinforcement Learning
arXiv 2610.05819 · 2026-10-06守卫漏掉的，机器人执行：VLA指令中的隐含危害
What the Guard Misses, the Robot Executes: Implied Harm in VLA Instructions
arXiv 2610.05818 · 2026-10-06纳什均衡文本：一种用于文本生成的博弈论解码框架
Nash Equilibrium Text: A Game-Theoretic Decoding Framework for Text Generation
arXiv 2610.05817 · 2026-10-06Token扩散的层级（Level-of-Token Diffusion）
Level-of-Token Diffusion
arXiv 2610.05816 · 2026-10-06Plan Canvas：用于连续语言流的固定推理区域
Plan Canvas: Fixed Reasoning Regions for Continuous Language Flows
arXiv 2610.05815 · 2026-10-06退化布朗强迫下随机原始方程的谱间隙
Spectral gap for the stochastic primitive equations under degenerate Brownian forcing
arXiv 2610.05814 · 2026-10-06有限笛卡尔集上具有受限支撑和最大零点的多项式
Polynomials with restricted support and maximal zeros on a finite Cartesian set
arXiv 2610.05813 · 2026-10-06用于参数提取和缺陷检测的机器学习特征识别
Feature identification for parameter extraction and defect detection using machine learning
arXiv 2610.05812 · 2026-10-06在线AutoML：评估物联网网络中对抗训练防御策略的投毒攻击
Online AutoML: Evaluating Poisoning Attacks on Adversarial Training Defense Strategy in IoT Networks
arXiv 2610.05810 · 2026-10-06先进半导体节点的图像分辨率增强
Image resolution enhancement for advanced semiconductor nodes
arXiv 2610.05809 · 2026-10-06DiMOS：面向科学设计的Doob引导推理时多目标搜索
DiMOS: Doob-Guided Inference-Time Multi-Objective Search for Scientific Design
arXiv 2610.05808 · 2026-10-06日志异常检测的协议敏感性评估：HDFS 和 BGL 上的组件成本与目标访问敏感性
Protocol-Sensitive Evaluation of Log Anomaly Detection: Component Costs and Target-Access Sensitivity on HDFS and BGL
arXiv 2610.05807 · 2026-10-06高阶网络上求解线性方程的量子复杂性
Quantum Complexity of Solving Linear Equations on Higher-Order Networks
arXiv 2610.05806 · 2026-10-06时间度量空间与时间迭代函数系统
Temporal Metric Spaces and Temporal Iterated Function Systems
arXiv 2610.05805 · 2026-10-06小突变率下的多类型分支扩散
Multi-type branching diffusions with small mutation rates
arXiv 2610.05804 · 2026-10-06涉及理想幂的（上）同调模的渐近Castelnuovo-Mumford正则性
Asymptotic Castelnuovo-Mumford regularity of (co)homology modules involving powers of ideals
arXiv 2610.05803 · 2026-10-06非径向解在$\dot{H}^{1/2}$临界和超临界非线性下四阶薛定谔方程的散射
Scattering of non-radial solutions for the fourth-order Schrödinger equation with $\dot{H}^{1/2}$-critical and supercritical nonlinearity
arXiv 2610.05802 · 2026-10-06高斯映射变分用于图像去噪：几何分析与Anderson加速的Majorization-Minimization方法
Gauss-Map Variation for Image Denoising: Geometric Analysis and an Anderson--Accelerated Majorization--Minimization Method
arXiv 2610.05801 · 2026-10-06通过条件门控实现低秩自适应的自适应利用
Adaptive Utilization of Low-Rank Adaptation via Conditioned Gating
arXiv 2610.05800 · 2026-10-06Palatini Kalb-Ramond引力中的精确黑洞解
Exact black hole solutions in Palatini Kalb-Ramond gravity
arXiv 2610.05799 · 2026-10-06爱因斯坦-麦克斯韦求和规则与光滑膜不可能定理的持续性
Einstein--Maxwell Sum Rules and the Persistence of the Smooth-Brane No-Go Theorem
arXiv 2610.05798 · 2026-10-06严格反馈系统的部分状态死区自适应扰动抑制控制
Partial-State Deadzone-Adapted Disturbance Suppression Control For Strict-Feedback Systems
arXiv 2610.05797 · 2026-10-06动力学感知的自适应走廊与可行性扰动信赖域序列二次规划用于认证非完整运动规划
Dynamics-Aware Adaptive Corridors with Feasibility-Perturbed Trust-Region SQP for Certified Nonholonomic Motion Planning
arXiv 2610.05796 · 2026-10-06Ricci-平坦Kähler 4-流形基本群的不稳定性
Instability of the Fundamental Group for Ricci-Flat Kähler 4-Manifolds
arXiv 2610.05795 · 2026-10-06原子特征的可检验理论
A Testable Theory of Atomic Features
arXiv 2610.05794 · 2026-10-06拓扑条件后门：语言模型在推断处于多智能体系统时插入漏洞
Topology-Conditioned Backdoors: Language Models That Insert Vulnerabilities When They Infer They Are in a Multi-Agent System
arXiv 2610.05793 · 2026-10-06DASH：面向串联连杆与仿人机器人的达芬奇适配器，作为手术机器人研究的可及平台
DASH: A da Vinci Adapter for Serial-link and Humanoid Robots as an Accessible Platform for Surgical Robotics Research
arXiv 2610.05792 · 2026-10-06Omura 强逆指数的紧性及容量以上的临界速率
On the Tightness of Omura's Strong Converse Exponent and Critical Rates Above Capacity
arXiv 2610.05791 · 2026-10-06FairRSFM：面向遥感基础模型的生物群系感知基准与去偏框架
FairRSFM: A Biome-Aware Benchmark and Debiasing Framework for Remote Sensing Foundation Models
arXiv 2610.05790 · 2026-10-06无维度依赖的分布式非光滑非凸随机优化
Dimension-Free Decentralized Nonsmooth Nonconvex Stochastic Optimization
arXiv 2610.05789 · 2026-10-06基于有限状态机的多引擎分析平台流量编排
Finite State Machine-Based Traffic Orchestration for Multi-Engine Analysis Platforms
arXiv 2610.05788 · 2026-10-06约束感知的代码混合低资源环境下的对话式职位推荐
Constraint-Aware Conversational Job Recommendation in Code-Mixed Low-Resource Settings
arXiv 2610.05787 · 2026-10-06池式研究核反应堆的自适应控制：理论极限、务实执行约束及实现的性能与自适应
Adaptive control of pool-type research nuclear reactors: theory limits, pragmatic actuation constraints, and realized performance and adaptation
arXiv 2610.05786 · 2026-10-06拒绝服务攻击下非线性多智能体系统事件触发预设时间一致性跟踪的分离原理
Separation Principle for Event-Triggered Prescribed-Time Consensus Tracking of Nonlinear Multi-Agent Systems under DoS Attacks
arXiv 2610.05785 · 2026-10-06更高的闭零理想（类）
The Higher Closed Null Ideal(s)
arXiv 2610.05784 · 2026-10-06CLARA：AI能否评估儿童故事的发展适宜性？
CLARA: Can AI Assess Developmental Appropriateness in Children's Stories?
arXiv 2610.05783 · 2026-10-06Agentic-ZTA：一种用于自主零信任实施的多智能体架构
Agentic-ZTA: A Multi-Agent Architecture for Autonomous Zero Trust Enforcement
arXiv 2610.05782 · 2026-10-06相对几何 Langlands 中的自守换位子关系
Automorphic commutator relations in relative geometric Langlands
arXiv 2610.05781 · 2026-10-06各向同性高斯过程改进高维朴素贝叶斯优化
Isotropic Gaussian Processes Improve Vanilla Bayesian Optimization in High Dimensions
arXiv 2610.05780 · 2026-10-06面向AI生成视频的时空语义重要性引导的统一压缩与编辑框架
A Spatiotemporal Semantic Importance-Guided Unified Compression and Editing Framework for AI-Generated Videos
arXiv 2610.05779 · 2026-10-06
