2026-07论文中文摘要
深入技能市场：从软件工程活动到可复用的智能体技能
Inside the Skill Market: From Software Engineering Activities to Reusable Agent Skills
arXiv 2607.09065 · 2026-07-13超重暗亮孤子作为谐波捕获玻色混合物中空间对称破缺转变的标志
Superheavy dark-bright soliton as a signature of spatial symmetry breaking transition in harmonically trapped Bose mixtures
arXiv 2607.09064 · 2026-07-13EvoLP：实时边缘系统中用于模型压缩的自进化延迟预测器
EvoLP: Self-Evolving Latency Predictor for Model Compression in Real-Time Edge Systems
arXiv 2607.09063 · 2026-07-13通过单调性谱采样方法对弹性不可穿透散射体进行稳健形状重建
Robust shape reconstruction of elastic impenetrable scatterers via monotonicity spectral sampling methods
arXiv 2607.09062 · 2026-07-13关于视觉推理中的局部性和长度泛化
On Locality and Length Generalization in Visual Reasoning
arXiv 2607.09061 · 2026-07-13ARCANA：用于ARC-AGI-2推理的反射式多智能体程序合成框架
ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning
arXiv 2607.09059 · 2026-07-13用于电流受限型并网逆变器故障后恢复的结构解耦与电流角度控制
Structural Decoupling and Current-Angle Steering for Post-Fault Recovery of Current-Limited Grid-Forming Inverters
arXiv 2607.09058 · 2026-07-13STEAM：基于弹性匹配和自适应净化的稳定自训练
STEAM: Stable Self-Training with Elastic Matching and Adaptive Purification
arXiv 2607.09057 · 2026-07-13铝体相和界面处可忽略的电流感应扭矩
Negligible current-induced torque from the bulk and interface of Al
arXiv 2607.09055 · 2026-07-13自动化即时Python类型注释更新
Automating Just-In-Time Python Type Annotation Updating
arXiv 2607.09054 · 2026-07-13一种新兴的海市蜃楼：新兴的错位与重新对齐真的是一种稳健的现象吗？
An Emergent Mirage: Is Emergent Misalignment and Realignment Indeed a Robust Phenomenon?
arXiv 2607.09053 · 2026-07-13COBS：累积阶数块稀疏注意力
COBS: Cumulant Order Block Sparse Attention
arXiv 2607.09052 · 2026-07-13通过自适应变分量子轨迹压缩模拟林德布拉德动力学
Simulation of Lindbladian dynamics via adaptive variational quantum trajectory compression
arXiv 2607.09051 · 2026-07-13色散波区域中良好Boussinesq方程解的渐近稳定性
Asymptotic stability of solutions to the good Boussinesq equation in dispersive wave region
arXiv 2607.09050 · 2026-07-13关于有界 VC 维数图的单指数 Erdős--Hajnal 界
A Single-Exponential Erdős--Hajnal Bound for Graphs of Bounded VC-Dimension
arXiv 2607.09049 · 2026-07-13拉梅超椭圆周长的超几何级数表示
Hypergeometric Series Representations for the Perimeter of Lamé Superellipses
arXiv 2607.09048 · 2026-07-13经典可实现的不相容性
Classically Realizable Incompatibility
arXiv 2607.09047 · 2026-07-13用于全动力学离子和漂移动力学电子模拟的隐式离散化方案
Implicit discretization schemes for full-kinetic ion and drift-kinetic electron simulations
arXiv 2607.09046 · 2026-07-13云能驱动自动驾驶吗？跨5G和6G卸载自动驾驶的基础设施可行性
Can the Cloud Drive? Infrastructure Feasibility of Offloading Autonomous Driving Across 5G and 6G
arXiv 2607.09045 · 2026-07-13一种用于扩展Fisher-Kolmogorov方程的线性化保结构混合虚拟元方法
A Linearized and structure-preserving mixed virtual element method for the extended Fisher-Kolmogorov equation
arXiv 2607.09044 · 2026-07-13MERL关于实时语音分离挑战提交的技术报告
Technical Report for MERL's Real-TSE Challenge Submission
arXiv 2607.09043 · 2026-07-13关于$f(\mathbb{Q})$引力的史瓦西分支上对数熵修正的热力学一致性及超辐射禁戒结果
Thermodynamic Consistency of Logarithmic Entropy Corrections on the Schwarzschild Branch of $f(\mathbb{Q})$ Gravity and a Superradiance No-Go Result
arXiv 2607.09041 · 2026-07-13差速旋转对中子星最大质量的影响
Effects of Differential Rotation on the Maximum Mass of Neutron Stars
arXiv 2607.09040 · 2026-07-13通过广义泊松流进行可变长度生成蛋白质设计
Variable-Length Generative Protein Design via Generalized Poisson Flow
arXiv 2607.09039 · 2026-07-13在线性空间上学习增强匹配的最优度量失真
Optimal Metric Distortion for Learning-Augmented Matching on the Line
arXiv 2607.09038 · 2026-07-13首次向超级KEKB高能环注入同步加速器束流
First Synchrotron Injection Attempt into The SuperKEKB High Energy Ring
arXiv 2607.09037 · 2026-07-13风暴眼中：极端可变外观活动星系核IC 3599的第三次巨型X射线爆发
In the Eye of the Storm: The Third Giant X-ray Outburst of the Extreme Changing-look AGN IC 3599
arXiv 2607.09036 · 2026-07-13多层低地球轨道卫星物联网星座的建模与分析
Modeling and Analysis for Multiple-Layer LEO Satellite Internet of Things Constellations
arXiv 2607.09035 · 2026-07-13凯勒流形上热方程正解的黑塞矩阵的上界
Upper Bounds for Hessian Matrices of Positive Solutions to Heat Equations on Kähler Manifolds
arXiv 2607.09034 · 2026-07-13关于一维随机热方程路径适定性的一个注记
A remark on pathwise well-posedness of the 1-$d$ stochastic heat equation
arXiv 2607.09033 · 2026-07-13作为上下文逻辑的量子逻辑
Quantum Logic as the Logic of Contexts
arXiv 2607.09032 · 2026-07-13关于有向图中广义拟核的三个结果
Three Results on Generalized Quasikernels in Digraphs
arXiv 2607.09031 · 2026-07-13低地球轨道卫星星座中连续孔径阵列辅助的集成通信与导航
Continuous Aperture Array-Assisted Integrated Communication and Navigation in LEO Satellite Constellations
arXiv 2607.09030 · 2026-07-13MOSAIC：用于高效异构视觉语言模型的自适应层间组合
MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models
arXiv 2607.09029 · 2026-07-13关于单项式理想的微分幂滤过的F - 阈值
On $F$-thresholds of differential power filtrations
arXiv 2607.09028 · 2026-07-13散射与逆散射中的分裂角
Split Corners in Scattering and Inverse Scattering
arXiv 2607.09027 · 2026-07-13高维几何植入匹配：多视图的力量
Geometric planted matchings in high dimensions: The power of multiple views
arXiv 2607.09026 · 2026-07-13科学发现的进化智能：从进化计算到累积发现系统
Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems
arXiv 2607.09025 · 2026-07-13视频生成模型是通用视觉学习者
Video Generation Models are General-Purpose Vision Learners
arXiv 2607.09024 · 2026-07-13周期调制的Korteweg-de Vries方程的精细整体适定性
Refined global well-posedness for the periodic modulated Korteweg-de Vries equation
arXiv 2607.09023 · 2026-07-13隐私侦探：一款通过利用法律文件培养学生开发者隐私意识的叙事游戏
Privacy Detective: A Narrative Game that Cultivates Student Developers' Privacy Awareness by Harnessing Legal Documents
arXiv 2607.09022 · 2026-07-13恰当概型上的渐近上同调函数与体积
Asymptotic Cohomological Functions and Volumes on Proper Schemes
arXiv 2607.09021 · 2026-07-13通过音系激活映射进行音素分割与识别
Phone Segmentation and Recognition through Phonological Activation Mapping
arXiv 2607.09020 · 2026-07-13反常霍尔效应的新视角
A new perspective on the anomalous Hall effect
arXiv 2607.09019 · 2026-07-13人类对人工智能生成的设计变体选择中的集中趋势偏差
Central Tendency Bias in Human Selection of AI-Generated Design Variations
arXiv 2607.09018 · 2026-07-13基于图分解的无蜂窝网络混合整数优化研究
Study of Mixed-Integer Optimization Based on Graph-Based Decomposition for Cell-Free Networks
arXiv 2607.09017 · 2026-07-13SLBench：评估大语言模型智能体在技能中遵循逻辑关系的情况
SLBench: Evaluating How LLM Agents Follow Logical Relations in Skills
arXiv 2607.09016 · 2026-07-13用于大语言模型路由的具有替代奖励的相关感知上下文博弈
Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing
arXiv 2607.09015 · 2026-07-13离散盒子{0,1,2}^d的双覆盖的新界值
New bounds for double covers of the discrete box {0,1,2}^d
arXiv 2607.09014 · 2026-07-13正交设计矩阵加速贝叶斯半参数回归
Orthogonalized Design Matrices Speed-ups of Bayesian Semiparametric Regression
arXiv 2607.09013 · 2026-07-13
