2026-09论文中文摘要
提示词中自然语言差异对基于LLM的自动代码生成影响的研究
A Study on the Impact of Natural Language Differences in Prompts on Automatic Code Generation Using LLMs
arXiv 2609.18311 · 2026-09-17轮转均衡：少量次可加智能体的计算困难性与公平性
Equilibria of Round-Robin: Computational Hardness and Fairness for Few Subadditive Agents
arXiv 2609.18309 · 2026-09-17线性动力系统的预测式在线扰动-动作控制
Predictive Online Disturbance-Action Control for Linear Dynamical Systems
arXiv 2609.18307 · 2026-09-17多智能体网络中的偏差放大：有偏智能体如何塑造观点与修辞
Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric
arXiv 2609.18306 · 2026-09-17SemISAC：语义集成感知与通信
SemISAC: Semantic Integrated Sensing and Communications
arXiv 2609.18305 · 2026-09-17视觉自回归先验用于RAW到sRGB图像信号处理
Visual Autoregressive Priors for RAW-to-sRGB Image Signal Processing
arXiv 2609.18302 · 2026-09-17OGLE、KMTNet和DREAMS观测到的两颗蓝色大振幅脉动星中的模式切换
Mode Switching in Two Blue Large Amplitude Pulsators observed by OGLE, KMTNet and DREAMS
arXiv 2609.18300 · 2026-09-17具有 $\ell_1$ 偏好的分数分配
Fractional Assignment with $\ell_1$ Preferences
arXiv 2609.18299 · 2026-09-17用于实时赞助搜索广告的一步检索框架：基于层次化文本表示
One-Step Retrieval Framework for Real-Time Sponsored Search Ads Using Hierarchical Text Representations
arXiv 2609.18296 · 2026-09-17保持功能的零样本真实-仿真-真实操作数据生成
Function-Preserving Data Generation for Zero-Shot Real-to-Sim-to-Real Manipulation
arXiv 2609.18293 · 2026-09-17标量曲率喷流的全局可度量化性
Global Metrizability on Sprays of Scalar Curvature
arXiv 2609.18292 · 2026-09-17基于关系引导的LLM用例建模
Relationally Guided Use Case Modeling with LLMs
arXiv 2609.18291 · 2026-09-17将德国联邦议院演讲者关联至 Wikidata：元数据的范围与覆盖度
Linking Speakers of the German Parliament to Wikidata: Scope and Coverage of Metadata
arXiv 2609.18289 · 2026-09-17什么构成策略推理？关于人类、引擎和语言模型的国际象棋研究的系统映射
What Counts as Strategic Reasoning? A Systematic Mapping of Chess Research on Humans, Engines, and Language Models
arXiv 2609.18286 · 2026-09-17作为高阶微分形式的暗物质
Dark matter as higher-form fields
arXiv 2609.18285 · 2026-09-17匈牙利制造：对生成式语言模型性能的评论
Made in Hungary: Comments on the performance of generative language models
arXiv 2609.18284 · 2026-09-17智能体应部署在哪里？边缘-云连续体中智能体AI的能量-内存特征分析
Where Should Agents Live? Energy-Memory Characterization of Agentic AI for the Edge-Cloud Continuum
arXiv 2609.18283 · 2026-09-17好得难以置信？诊断并缩小AI偏好与真实用户参与度之间的差距
Too Good to Be Real? Diagnosing and Reducing the Gap Between AI Preference and Real User Engagement
arXiv 2609.18282 · 2026-09-17基于生成对抗网络的鲁棒DDoS攻击检测框架
A GAN-Based Framework for Robust DDoS Attack Detection
arXiv 2609.18281 · 2026-09-17Poiseuille流附近的稳态对称Navier-Stokes流：存在性与粘性消失极限
Steady symmetric Navier-Stokes flow near Poiseuille flow: existence and vanishing viscosity limit
arXiv 2609.18280 · 2026-09-17面向视觉Transformer的解码器无关令牌合并：G2TM的系统性研究
Decoder-Agnostic Token Merging for Vision Transformers: A Systematic Study of G2TM
arXiv 2609.18279 · 2026-09-17六维$q$-形式场通过引力耦合约化为四维场
Reduction of the six-dimensional $q$-form fields to the four-dimensional fields by coupling with gravity
arXiv 2609.18277 · 2026-09-17多智能体网络中广义速度刚性的宏观运动模式
Macroscopic Motion Patterns from Generalized Velocity Rigidity in Multi-Agent Networks
arXiv 2609.18276 · 2026-09-17见证加密：基于素数阶通用群
Witness Encryption via Prime-Order Generic Groups
arXiv 2609.18275 · 2026-09-17我编码还是AI编码：课堂观察中AI评分与人类评分的比较评估
I code or AI code: A comparative evaluation of AI-rated scores in classroom observations
arXiv 2609.18274 · 2026-09-17网页浏览中的行为指纹识别与导航预测
Behavioral Fingerprinting and Navigation Prediction in Web Browsing
arXiv 2609.18273 · 2026-09-17谁审计谁，在什么基座上，用什么证据？一种面向智能体AI的独立性分级审计协议
Who Audits Whom, on What Substrate, with What Evidence? An Independence-Graded Audit Protocol for Agentic AI
arXiv 2609.18272 · 2026-09-17有限 Apéry 极限的 $q$-递推关系
A $q$-recurrence for a finite Apéry limit
arXiv 2609.18271 · 2026-09-17BENCHCOMPASS：从分数到信号——面向支付领域大语言模型的训练与部署决策
BENCHCOMPASS: From Scores to Signals for Training and Harness Decisions in Payment-Domain LLMs
arXiv 2609.18270 · 2026-09-17前向固定耦合BFKL核的Lévy结构及对称方案中正定性的固定阶障碍
Lévy structure of the forward fixed-coupling BFKL kernel and a fixed-order obstruction to positivity in the symmetric scheme
arXiv 2609.18269 · 2026-09-17状态不确定性下安全性的递归CBF框架
A Recursive CBF Framework for Safety under State Uncertainty
arXiv 2609.18268 · 2026-09-17封闭重复使用量子信道时的浴维数与初始熵
Bath dimension and initial entropy for closed repeated use of a quantum channel
arXiv 2609.18267 · 2026-09-17Pogorelov 内部估计与复 Monge-Ampère 方程的 Liouville 定理
Pogorelov interior estimates and a Liouville theorem for the complex Monge--Ampère equation
arXiv 2609.18265 · 2026-09-17自主控制系统韧性的指标
Indicators of resilience for autonomous control systems
arXiv 2609.18264 · 2026-09-17用精密物质与反物质实验探测洛伦兹破缺标量力与暗物质
Probing Lorentz-violating scalar forces and dark matter with precision matter and antimatter experiments
arXiv 2609.18263 · 2026-09-17REPAIR：通过事实验证的迭代细化解决科学检索器中的长尾混淆问题
REPAIR: Resolving Long-Tail Confusion in Scientific Retrievers via Fact-Verified Iterative Refinement
arXiv 2609.18262 · 2026-09-17Lean 中的描述复杂性：通过一阶归约的完备性
Descriptive Complexity in Lean: Completeness by First-Order Reductions
arXiv 2609.18261 · 2026-09-17MS-RFD：基于重建3D轨迹的链球多信号释放帧检测
MS-RFD: Multi-Signal Release Frame Detection in Hammer Throw from Reconstructed 3D Trajectories
arXiv 2609.18260 · 2026-09-17吸引-排斥趋化系统中大时间行为
Large-time behavior in an attraction--repulsion chemotaxis system
arXiv 2609.18258 · 2026-09-17伪增量性检验：从自然发生的干预中测量广告增量效应
Pseudo-Incrementality Testing: Measuring Advertising Lift from Naturally Occurring Interventions
arXiv 2609.18257 · 2026-09-17演化错误状态：面向超声病灶分割的故障感知渐进修复
Evolving Error States: Failure-Aware Progressive Repair for Ultrasound Lesion Segmentation
arXiv 2609.18256 · 2026-09-17广义拉马努金整函数的连接公式
Connection Formulae for a Generalised Ramanujan Entire Function
arXiv 2609.18255 · 2026-09-17交换环的有限内射维数超过有限射影维数
Finitistic injective dimension exceeding finitistic projective dimension for a commutative ring
arXiv 2609.18254 · 2026-09-17有限型曲面上的Anosov微分同胚
Anosov Diffeomorphisms of Finite-Type Surfaces
arXiv 2609.18253 · 2026-09-17有界闭凸集超空间的满射 Hausdorff 等距
Surjective Hausdorff Isometries of Hyperspaces of Bounded Closed Convex Sets
arXiv 2609.18252 · 2026-09-17量子概率流引导的激发输运耦合控制自由度约简
Quantum Probability Current Guided Reduction of Coupling Control Degrees of Freedom for Excitation Transport
arXiv 2609.18250 · 2026-09-17Re2A：基于评分标准偏好推理与对齐的情境化对话推荐
Re2A: Situated Conversational Recommendation via Rubric-based Preference Reasoning and Alignment
arXiv 2609.18249 · 2026-09-17Quanta：一个用于量化嵌入、词汇索引和知识图谱混合检索的自包含Python库
Quanta: A Self-Contained Python Library for Hybrid Retrieval over Quantised Embeddings, Lexical Indexes, and Knowledge Graphs
arXiv 2609.18248 · 2026-09-17探测超新星星周介质中511 keV谱线的微弱相互作用粒子
Probing Feebly Interacting Particles with 511 keV Line from Circumstellar Medium of Supernovae
arXiv 2609.18247 · 2026-09-17A3P5 NEMESIS 集成漫游车设计：用于环境侦察与机器人采样，具备可复现的移动性分析和外部数据机器学习校准基准
A3P5 NEMESIS Integrated Rover Design for Environmental Reconnaissance and Robotic Sampling with Reproducible Mobility Analysis and an External Data Machine Learning Calibration Benchmark
arXiv 2609.18245 · 2026-09-17
