2026-09论文中文摘要
ARIA — 用于信息娱乐系统自主测试的智能体框架
ARIA - An Agentic Framework for Autonomous Testing of Infotainment Systems
arXiv 2609.04913 · 2026-09-07TreeFI：面向深度神经网络的值感知统计故障注入
TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks
arXiv 2609.04912 · 2026-09-07基于Flash Attention的快速高斯和计算
Fast Gauss Sums via Flash Attention
arXiv 2609.04910 · 2026-09-07基于魏尔显式公式构造有限希尔伯特-波利亚矩阵
Construction of Finite Hilbert--Pólya Matrices from Weil's Explicit Formula
arXiv 2609.04908 · 2026-09-07纳米尺度下的微开尔文分辨率测温
Microkelvin resolution thermometry at the nanometre scale
arXiv 2609.04907 · 2026-09-07基于未正射校正影像的星载甲烷检测
Methane Detection On Board Satellites from Unorthorectified Imagery
arXiv 2609.04906 · 2026-09-07辅助量子比特介导的开放量子系统稳态工程
Ancilla mediated steady-state engineering in open quantum systems
arXiv 2609.04905 · 2026-09-07CPL：一种具有显式底层控制的类C紧凑系统语言
CPL: A Compact C-like Systems Language with Explicit Low-Level Control
arXiv 2609.04904 · 2026-09-07InterSing：用于3D二重唱动画及更广泛应用的显式交互动力学框架
InterSing: Explicit Interaction Dynamics for 3D Duet Singing Animation and Beyond
arXiv 2609.04903 · 2026-09-07基于声音的多人三维姿态估计
Sound-based Multi-Person 3D Pose Estimation
arXiv 2609.04902 · 2026-09-07用连续引力波探测致密天体的磁场
Probing magnetic fields of compact objects with continuous gravitational waves
arXiv 2609.04900 · 2026-09-07安全特征定位问题
The Security Feature Location Problem
arXiv 2609.04899 · 2026-09-07RefactorPlatform：用于仓库级重构智能体可控评估的开源工具
RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents
arXiv 2609.04898 · 2026-09-07盘扩散冻结过稳定共振天平动
Disk dispersal freezes overstable resonant librations
arXiv 2609.04897 · 2026-09-07神经网络学习从量子边际重建多体纠缠
Neural networks learn to reconstruct multipartite entanglement from quantum marginals
arXiv 2609.04896 · 2026-09-07从语言模型到世界行动系统：智能体AI在数字、社交、虚拟和物理环境中的进展与局限
From Language Models to World-Acting Systems: Progress and Limits of Agentic AI across Digital, Social, Virtual, and Physical Environments
arXiv 2609.04894 · 2026-09-07无推理成本的推理：面向机器人VLA策略的潜在语义支架
Reasoning Without Inference Cost: Latent Semantic Scaffolding for Robot VLA Policies
arXiv 2609.04893 · 2026-09-07量化超大质量恒星形成中碰撞驱动的质量损失：恒星结构的作用
Quantifying collision-driven mass loss in supermassive star formation: the role of stellar structure and accretion
arXiv 2609.04892 · 2026-09-07颈动脉四维血流磁共振成像的注意力引导超分辨率
Attention-guided super-resolution of 4D flow MRI in carotid arteries
arXiv 2609.04891 · 2026-09-07利用三元队列寻找多个重叠的稠密子图
Finding Many Overlapping Dense Subgraphs Using Triadic Cohorts
arXiv 2609.04890 · 2026-09-07法正态映射锥的有限角重构与分离
Finite-Corner Reconstruction and Separation for Cones of Normal Maps
arXiv 2609.04889 · 2026-09-07稳态受迫水波问题中的同宿脱落现象
Homoclinic-shedding in the steady forced water-wave problem
arXiv 2609.04888 · 2026-09-07探测前沿处的宜居带类地行星：针对PLATO M型矮星样本的凌星搜索 pipeline 的实测完整性与虚警率
Habitable-zone Earths at the detection frontier: Measured completeness and false-alarm rate of a transit pipeline for the PLATO M-dwarf sample
arXiv 2609.04887 · 2026-09-07超出领头阶的双强子碎裂函数
Di-hadron Fragmentation Functions beyond LO
arXiv 2609.04885 · 2026-09-07耦合端口哈密顿常微分方程的能量一致分裂与分解方法
Energy-Consistent Splitting and Decomposition Approaches for Coupled port-Hamiltonian ODEs
arXiv 2609.04884 · 2026-09-07非相对论共线磁体的多极自旋点群分类
Spin-Point-Group Classification of Multipoles for Nonrelativistic Collinear Magnets
arXiv 2609.04883 · 2026-09-07AtomRec：面向智能体推荐的演化原子记忆
AtomRec: Evolving Atomic Memory for Agentic Recommendation
arXiv 2609.04882 · 2026-09-07从深到浅：无约束且高效的层合并策略
From Deep to Shallow: Unconstrained and Efficient Layer Merging Strategy
arXiv 2609.04881 · 2026-09-07不确定性下的太阳能光伏政策序列设计：一种基于智能体的强化学习方法
Reinforcement Learning for Sequential Solar PV Policy Design under Uncertainty: An Agent-Based Approach
arXiv 2609.04880 · 2026-09-07ReCAST：面向混淆短信风险分类的感知恢复级联分阶段训练
ReCAST: Restoration-aware Cascaded Stage-wise Training for Obfuscated SMS Risk Classification
arXiv 2609.04878 · 2026-09-07MARLA：欧盟人工智能法案下监管学习的概念框架
MARLA: A Conceptual Scaffold for Regulatory Learning under the EU AI Act
arXiv 2609.04877 · 2026-09-07动态环境中基于AFDM的集成感知与通信（ISAC）：基础、技术与机遇
AFDM-Enabled ISAC in Dynamic Environments: Fundamentals, Technologies and Opportunities
arXiv 2609.04876 · 2026-09-07无需重启的遗忘：有状态大语言模型智能体的执行状态遗忘
Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents
arXiv 2609.04875 · 2026-09-07用于光数据中心网络的波长借用架构——扩展版
A Wavelength Borrowing Architecture for Optical Data Center Networks - Extended Version
arXiv 2609.04874 · 2026-09-07正弦-戈登方程动力学中不稳定性前沿的演化
Evolution of instability fronts in sine-Gordon equation dynamics
arXiv 2609.04873 · 2026-09-07理论与计算研究中的生成式AI淘金热
The Generative AI Gold Rush in Theoretical and Computational Research
arXiv 2609.04872 · 2026-09-07AutoLR：自动化工业推荐系统中从研究到上线评审的路径
AutoLR: Automating the Path from Research to Launch Review in Industrial Recommender Systems
arXiv 2609.04871 · 2026-09-07CHAMP：用于在线多人游戏中匹配与预测的跨域混合架构
CHAMP: Cross-domain Hybrid Architecture for Matchmaking and Prediction in Online Multi-Player Games
arXiv 2609.04870 · 2026-09-07从交互轨迹到持久技能：计算机使用智能体的在线演化
From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents
arXiv 2609.04869 · 2026-09-07胶子融合产生希格斯玻色子对：高阶修正与理论不确定性
Higgs Boson Pair Production via Gluon Fusion: Higher-Order Corrections and Theoretical Uncertainties
arXiv 2609.04868 · 2026-09-07大型语言模型（LLM）辅助的基于智能体的能源采用模型的行为与情景增强
LLM-Assisted Behavioural and Scenario Augmentation for Agent-Based Energy Adoption Models
arXiv 2609.04866 · 2026-09-07MZ-Rain：用于站点级降水临近预报的 moisture-budget 引导零膨胀模型
MZ-Rain: Moisture-Budget-Guided Zero-Inflated Model for Station-Level Precipitation Nowcasting
arXiv 2609.04864 · 2026-09-07用于纳米光子散射的高效精简模型：为超表面设计优化全局极化率矩阵
Frugal Effective Models for Nanophotonic Scattering: Optimizing Global Polarizability Matrices for Metasurface Design
arXiv 2609.04863 · 2026-09-07用于缓解多任务推荐中信号侵蚀的个性化任务依赖图
Personalized Task Dependency Graphs for Mitigating Signal Erosion in Multi-Task Recommendation
arXiv 2609.04862 · 2026-09-07当基因组掩码先验无法迁移时：强变异预测，弱功能生成
When Genomic Masking Priors Fail to Transfer: Strong Variant Prediction, Weak Functional Generation
arXiv 2609.04861 · 2026-09-07缓解跨域3D类增量学习中的性能差异
Mitigating Performance Discrepancy in Cross-Domain 3D Class-Incremental Learning
arXiv 2609.04860 · 2026-09-07具有最多不动点的金字塔型阿达马设计的刻画
Characterizing pyramidal Hadamard designs with the largest number of fixed points
arXiv 2609.04858 · 2026-09-073千秒差距以外45个疏散星团的成员确定
Membership Determination of 45 Open Clusters Beyond 3 kpc
arXiv 2609.04857 · 2026-09-07二维中具有可逆自发曲率的半柔性聚合物的弹性
The elasticity of semiflexible polymers with reversible spontaneous curvature in two dimensions
arXiv 2609.04856 · 2026-09-07CC-Mediation：评估大型语言模型的跨文化冲突调解
CC-Mediation: Evaluating Large Language Models for Cross-Cultural Conflict Mediation
arXiv 2609.04855 · 2026-09-07
