2026-08论文中文摘要
基于微服务的软件定义车辆中的时序可变性研究综述
A Survey of Timing Variability in Microservice-Based Software-Defined Vehicles
arXiv 2608.23649 · 2026-08-26显式离散拟波兰空间与紧豪斯多夫空间的有效拟波兰范畴
Effective quasi-Polish categories of overt discrete spaces and compact Hausdorff spaces
arXiv 2608.23648 · 2026-08-26MolEmb：多模态大语言模型可作为强大的分子嵌入模型
MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Models
arXiv 2608.23646 · 2026-08-26乌尔都语中主要动词与轻动词区分的上下文嵌入证据
Contextual Embedding Evidence for Main--Light Verb Distinctions in Urdu
arXiv 2608.23645 · 2026-08-26伦理大语言模型辅助研究：负责任委托、验证与认知价值框架
Ethical LLM-Assisted Research: A Framework for Responsible Delegation, Verification, and Epistemic Value
arXiv 2608.23644 · 2026-08-26FLARE：一种用于循证采用医疗人工智能的系统性不确定性感知框架
FLARE: A Systematic, Uncertainty-Aware Framework for Evidence-Based Adoption of Artificial Intelligence in Healthcare
arXiv 2608.23643 · 2026-08-26测得的AI偏好中有多少来自模型，又有多少来自测量工具？
How much of a measured AI preference is the model, and how much is the instrument?
arXiv 2608.23641 · 2026-08-26审计合成回忆录：对照人生的文献记录，测量大语言模型生成自传中的场景层面虚构
Auditing the Synthetic Memoir: Measuring Scene-Level Confabulation in LLM-Generated Autobiography Against the Documented Record of the Life It Describes
arXiv 2608.23640 · 2026-08-26关系型GNS融合与幂等规范-引力不动点
Relational GNS Fusion and an Idempotent Gauge-Gravity Fixed Point
arXiv 2608.23639 · 2026-08-26可复现的共形预测
Replicable Conformal Prediction
arXiv 2608.23638 · 2026-08-26用于形状控制曲线设计的三参数二元细分格式
A Three-Parameter Binary Subdivision Scheme for Shape-Controlled Curve Design
arXiv 2608.23637 · 2026-08-26ToolRobustBench：工具调用智能体的分阶段扰动评估与故障诊断
ToolRobustBench: Stage-Wise Perturbation Evaluation and Failure Diagnosis for Tool-Calling Agents
arXiv 2608.23635 · 2026-08-26混合比例并非性能所在：诊断视觉-语言模型少样本适配中的原型混合
The Blending Ratio Is Not Where the Performance Is: Diagnosing Prototype Blending for Few-Shot Adaptation of Vision-Language Models
arXiv 2608.23634 · 2026-08-26基于DESI-DR2测量结果检验运行真空模型
Testing the running vacuum model in light of DESI-DR2 Measurements
arXiv 2608.23633 · 2026-08-26用于代码偏好优化的函数级执行反馈
Function-Level Execution Feedback for Code Preference Optimization
arXiv 2608.23632 · 2026-08-26TRACE：面向多目标材料发现的过渡感知残差控制
TRACE: Transition-Aware Residual Control for Multi-Objective Materials Discovery
arXiv 2608.23631 · 2026-08-26FPGAgent：一种用于FPGA环境中自主HLS代码生成与验证的大语言模型辅助框架
FPGAgent: An LLM-Assisted Framework for Autonomous HLS Code Generation and Verification in FPGA Environments
arXiv 2608.23630 · 2026-08-26可调用性并非可操作性：针对大语言模型智能体的受控接口干预
Callability Is Not Operability: Controlled Interface Interventions for LLM Agents
arXiv 2608.23628 · 2026-08-26从分诊到出院：急诊部门NLP任务、方法与开放挑战综述
From Triage to Discharge: A Survey of NLP Tasks, Methods, and Open Challenges in the Emergency Department
arXiv 2608.23627 · 2026-08-26天文基础模型中，巡天检测通道会覆盖像素并偏差层析平均红移
A survey detection channel overrides the pixels in an astronomical foundation model, and biases tomographic mean redshifts
arXiv 2608.23626 · 2026-08-26在含噪声的网络测量下分离时变网络构成与预测依赖关系
Separating Time-Varying Network Composition from Predictive Dependence under Noisy Network Measurement
arXiv 2608.23625 · 2026-08-26皮卡德机动的意外效果：看到同一艘超光速飞船的三个影像
The unexpected effectiveness of the Picard maneuver: Seeing three images of the same superluminal spaceship
arXiv 2608.23624 · 2026-08-26智能体何时可以停止？带证据的工具使用大语言模型终止机制
When May an Agent Stop? Evidence-Carrying Termination for Tool-Using LLMs
arXiv 2608.23623 · 2026-08-26大语言模型智能体使用模拟模型开展对照实验
LLM Agents Perform Controlled Experiments Using Simulation Models
arXiv 2608.23622 · 2026-08-26pro-p群的连续Mal'cev Qp完备化
Continuous Mal'cev Qp-Completion of Pro-p Groups
arXiv 2608.23621 · 2026-08-26二次非线性电动力学可积轨迹上的精确双荷黑洞
An exact dyonic black hole at the integrable locus of quadratic nonlinear electrodynamics
arXiv 2608.23620 · 2026-08-26识别代码的隐式声明式表示以辅助代码仓库迁移
Identifying Latent Declarative Representations of Code for Assisting Repository Migration
arXiv 2608.23619 · 2026-08-26采用遥测：基于生产信号衡量企业级AI的采用情况
Adoption Telemetry: Measuring Enterprise AI Adoption from Production Signals
arXiv 2608.23617 · 2026-08-26随机实验中的最优方差缩减
Optimal Variance Reduction in Randomized Experiments
arXiv 2608.23615 · 2026-08-26用于精密授时应用的SDR驱动程序
SDR Driver for Precise Timing Applications
arXiv 2608.23614 · 2026-08-26一种非线性动力学方法用于评估无创人体胃电图记录中的幅频耦合
A nonlinear dynamics approach to assess amplitude-frequency coupling in non-invasive human electrogastrography recordings
arXiv 2608.23613 · 2026-08-26基于SIMEX估计真实效应量分布
Estimating the True Effect Size Distribution with SIMEX
arXiv 2608.23612 · 2026-08-26REFINE：一种用于证据引导代码重构的多智能体大语言模型方法
REFINE: A Multi-Agent LLM Approach for Evidence-Guided Code Refactoring
arXiv 2608.23611 · 2026-08-26从可追溯性到可辩护性：智能体软件工程中的问责结构
From Traceability to Justifiability: Accountability Structures in Agentic Software Engineering
arXiv 2608.23610 · 2026-08-26面向DOM源粒子特效的浏览器管线架构分解：工作线程卸载、WebGL与WebAssembly
Decomposing Browser Pipeline Architectures for DOM-Sourced Particle Effects: Worker Offload, WebGL, and WebAssembly
arXiv 2608.23609 · 2026-08-26希格斯暴胀后的再加热
Reheating after the Higgs Inflation
arXiv 2608.23608 · 2026-08-26Herglotz $f(R,T)$引力的观测可行性：多探针贝叶斯分析
Observational viability of Herglotz $f(R,T)$ gravity: A multi-probe Bayesian analysis
arXiv 2608.23607 · 2026-08-26扩展位置动力学中的方向：应用于刚体与柯西拉杆
Orientation in Extended Position-Based Dynamics: Application to Rigid Bodies and Cosserat Rods
arXiv 2608.23606 · 2026-08-26用于活化截面测量的喷墨印刷靶的演示：氘核诱导锶反应至24 MeV
Demonstration of inkjet-printed targets for activation cross-section measurements: deuteron-induced reactions on strontium up to 24 MeV
arXiv 2608.23605 · 2026-08-26在LID-QMS分析期间，椭圆高斯激光束辐照下金属的气体释放
Gas release from metals under irradiation with elliptic Gaussian laser beam during LID-QMS analysis
arXiv 2608.23604 · 2026-08-26“精确实数计算”中的算法代价
Algorithmic Cost in "Exact Real Computation"
arXiv 2608.23603 · 2026-08-26StateTune：将大语言模型辅助的EDA流程调优转化为有状态的闭环过程
StateTune: Transforming LLM-Assisted EDA Flow Tuning into a Stateful, Closed-Loop Process
arXiv 2608.23601 · 2026-08-26正则模糊暗物质黑洞及其视界结构
Regular Fuzzy Dark Matter Black Holes and Their Horizon Structure
arXiv 2608.23600 · 2026-08-26压缩缓存，保留真相：基于测地线KV的单调等势分配
Squeezing the Cache, Preserving the Truth: Monotonic Equipotential Allocation with Geodesia-KV
arXiv 2608.23599 · 2026-08-26在谐振子动力学中探寻非对易与广义熵参数间的桥梁
Striving to find a bridge between noncommutative and generalized entropy parameters in the harmonic oscillator dynamics
arXiv 2608.23598 · 2026-08-26f(Q)宇宙学中曲率中性的一个不可能性定理？
A No-Go Theorem for Curvature Neutrality in f(Q) Cosmology?
arXiv 2608.23597 · 2026-08-26不合适的锁相放大导致饱和吸收光谱中的伪边峰
Artifact side peaks in saturated absorption spectroscopy caused by inappropriate lock-in amplification
arXiv 2608.23596 · 2026-08-26用于三维线性弹性问题的张量列车方法：块与全局算子表示及求解器性能分析
Tensor-Train Methods for 3D Linear Elasticity: Block and Global Operator Representations with Solver Performance Analysis
arXiv 2608.23595 · 2026-08-26从当前观测数据对拉斯特尔引力（Rastall gravity）的约束
Constraints on Rastall gravity from current observational data
arXiv 2608.23594 · 2026-08-26保真度偏好，而非人口统计学偏好：图像美学/偏好评分器的像素级属性敏感性审计
Fidelity Preference, Not Demographic Preference: A Pixel-Level Attribute-Sensitivity Audit of Image Aesthetic/Preference Scorers
arXiv 2608.23593 · 2026-08-26
