2026-09论文中文摘要
精确一次究竟在哪里实现？模型、执行框架与工具契约对LLM智能体重复副作用的影响
Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents
arXiv 2609.29095 · 2026-09-25太阳耀斑期间低电离层D区响应时间延迟的高度剖面
On the altitude profile of lower ionospheric D-region response time delay during solar flares
arXiv 2609.29094 · 2026-09-25DAWN：通过深度去噪世界模型实现噪声鲁棒的四足跑酷
DAWN: Noise-Robust Quadruped Parkour via Depth-Denoising World Models
arXiv 2609.29092 · 2026-09-25从被动执行到主动探索：真实环境中的智能体具身操作
From Passive Execution to Active Exploration: Agentic Embodied Manipulation in Realistic Environments
arXiv 2609.29091 · 2026-09-25经典语义抽取式摘要能否在印地语中评估？一项复制研究
Can Classical Semantic-Extractive Summarization Be Evaluated in Hindi? A Replication Study
arXiv 2609.29090 · 2026-09-25电子-空穴双层中的光诱导整流轨道磁化
Light-induced rectified orbital magnetization in electron-hole bilayers
arXiv 2609.29089 · 2026-09-25参数手性辛随机矩阵系综的卷绕数统计
Winding Number Statistics of a Parametric Chiral Symplectic Random Matrix Ensemble
arXiv 2609.29088 · 2026-09-25Wiener 调和空间上具有哈密顿量的薛定谔方程的正交 Strichartz 估计
Orthonormal Strichartz estimates for the Schrödinger equations with Hamiltonian on Wiener amalgam spaces
arXiv 2609.29085 · 2026-09-25在WeBe Band上训练和部署机器学习模型的快速流水线
A Rapid Pipeline for Training and Deploying ML Models on WeBe Band
arXiv 2609.29084 · 2026-09-25推进物理互联网与GraphRAG：一种回顾与整合现有研究的新方法
Advancing the Physical Internet with GraphRAG: A New Way to Review and Integrate Existing Research
arXiv 2609.29083 · 2026-09-25玻色子Kitaev链中的非平衡狄拉克凝聚体
Nonequilibrium Dirac condensate in bosonic Kitaev chain
arXiv 2609.29082 · 2026-09-25笛卡尔网格上可压缩Navier--Stokes方程的紧致高阶保正活性通量方法
A compact high-order and positivity-preserving active flux method for compressible Navier--Stokes equations on Cartesian meshes
arXiv 2609.29081 · 2026-09-25不要假装能做到：最后一英里配送中的司机不当行为
Don't Fake It If You Can't Make It: Driver Misconduct in Last-Mile Delivery
arXiv 2609.29080 · 2026-09-25电场驱动SrTiO3中的微观结构演化
Electric Current-Driven Microstructural Evolution in SrTiO3
arXiv 2609.29079 · 2026-09-25QCD 交叉跃迁传递函数：PTA 频段标量诱导引力波
QCD Crossover Transfer Functions for Scalar-Induced Gravitational Waves in the PTA Band
arXiv 2609.29078 · 2026-09-25CR流形上CR Dirac算子的Reilly型不等式及其应用
A Reilly-Type Inequality for CR Dirac Operators on CR Manifolds and Applications
arXiv 2609.29077 · 2026-09-25血脑屏障通透性的特征空间选择与异质性效应估计：从随机森林到广义随机森林的流程
Feature Space Selection and Heterogeneous Effect Estimation for Blood-Brain Barrier Permeability: A Random Forest to the Generalized Random Forest Pipeline
arXiv 2609.29076 · 2026-09-25CRISS：一种用于辅助癌症登记员的检索增强型AI聊天机器人
CRISS: A Retrieval-Augmented AI Chatbot for Assisting Cancer Registrars
arXiv 2609.29075 · 2026-09-25连续谱中束缚态的拓扑结构：来自主导辐射的角结构
Topology of bound states in the continuum from the angular structure of leading radiation
arXiv 2609.29074 · 2026-09-25看见不等于测量：面向视觉语言模型的工具增强度量空间推理
Seeing Is Not Measuring: Tool-Augmented Metric Spatial Reasoning for Vision-Language Models
arXiv 2609.29073 · 2026-09-25詹姆斯·韦布空间望远镜与极大望远镜观测高红移星系：迈向更精细的细节
High-z galaxies with the JWST and the ELT: Toward Ever-finer Detail
arXiv 2609.29072 · 2026-09-25另注：使用双流TFC-TDF U-Net与自适应集合归属的鲁棒性乐谱信息音符分离
On a Separate Note: Robust Score-Informed Note Separation with a Two-Stream TFC-TDF U-Net and Adaptive Set Ownership
arXiv 2609.29071 · 2026-09-25具有最大基数的正交量子拉丁方：基于满秩分解
Orthogonal Quantum Latin Squares with Maximal Cardinality from Full-Rank Factorizations
arXiv 2609.29070 · 2026-09-25BranchShine-CR：基于自条件CTC与一致性正则化的紧凑多语言国际音标转写
BranchShine-CR: Compact Multilingual IPA Transcription with Self-Conditioned CTC and Consistency Regularization
arXiv 2609.29069 · 2026-09-25软件工程自我效能感量表（SESES）的设计、开发及初步效度与信度证据
Design, development, and preliminary validity and reliability evidence of the Software Engineering Self-Efficacy Scale (SESES)
arXiv 2609.29068 · 2026-09-25TileBench：用于基于瓦片编程模型性能评估与瓶颈诊断的受控基准
TileBench: A Controlled Benchmark for Performance Evaluation and Bottleneck Diagnosis of Tile-Based Programming Models
arXiv 2609.29067 · 2026-09-25DA-GRD：面向感知-执行失配的决策感知抓取相关消歧，用于触觉恢复
DA-GRD: Decision-Aware Grasp-Relevant Disambiguation for tactile recovery under perception-to-execution mismatches
arXiv 2609.29065 · 2026-09-25EIB-Net：用于可泛化AI生成图像检测的熵引导信息瓶颈
EIB-Net: Entropy-Guided Information Bottleneck for Generalizable AI-Generated Image Detection
arXiv 2609.29064 · 2026-09-25人机二元互动中依恋与情感社会联结分类程序
A Procedure for Classifying Attachments and Affective Social Bonds in Human-Robot Dyads
arXiv 2609.29063 · 2026-09-25非多项式引力中理性正则黑洞的铃宕与灰体特征
Ringdown and greybody signatures of rational regular black holes in non-polynomial gravity
arXiv 2609.29062 · 2026-09-25人类与人工智能协作的多线任务调整：基于本地大语言模型与数字孪生
From Human Intent to Strategy Decisions: A Review Framework Integrating Large Language Models and Digital Twins
arXiv 2609.29061 · 2026-09-25Transformer作为跨任务学习者：共享结构驱动上下文学习中的样本效率
Transformers as Cross-Task Learners: Shared Structure Drives Sample Efficiency in In-Context Learning
arXiv 2609.29060 · 2026-09-25含反平方势的热方程的时间最优控制
Time optimal control for the heat equation with inverse-square potentials
arXiv 2609.29059 · 2026-09-25大都市人类流动性的玻璃态动力学：在引力平衡附近的冻结
Glassy dynamics of metropolitan human mobility frozen near the gravitational equilibrium
arXiv 2609.29057 · 2026-09-25Empath：追踪危机咨询对话中的多层次情绪动态
Empath: Tracing Multi-Level Emotion Dynamics in Crisis Counseling Dialogues
arXiv 2609.29056 · 2026-09-25基于引力波的广义相对论零检验
Null test of general relativity based on gravitational waves
arXiv 2609.29055 · 2026-09-25时间图中的零强制集
Zero Forcing Sets in Temporal Graphs
arXiv 2609.29054 · 2026-09-25相关无序链中的完美共振与脆弱局域化抑制
Perfect resonance and fragile localization suppression in correlated disordered chains
arXiv 2609.29053 · 2026-09-25从自蒸馏到自练习：多轮智能体的特权信息
From Self-Distillation to Self-Practice: Privileged Information for Multi-Turn Agents
arXiv 2609.29051 · 2026-09-25SLCA-GRPO：解决工具调用强化学习中的跨段信用分配错误
SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL
arXiv 2609.29050 · 2026-09-25无代理间通信的欧拉-拉格朗日多智能体系统仅基于方位的编队跟踪控制
Bearing-Only Formation Tracking Control for Euler-Lagrange Multi-Agent Systems Without Inter-Agent Communication
arXiv 2609.29049 · 2026-09-25幻觉的所在：VQ标记视觉语言模型中的跨架构电路
Where Hallucinations Live: A Cross-Architecture Circuit in VQ-Tokenized Vision-Language Models
arXiv 2609.29048 · 2026-09-25标准环面上Schrödinger极大估计的尖锐正则性阈值
A sharp regularity threshold for Schrödinger maximal estimates on standard tori
arXiv 2609.29047 · 2026-09-25二次引力中的物质密度扰动
Matter density perturbations in Quadratic Gravity
arXiv 2609.29046 · 2026-09-25令牌会记住：当分词绕过知识编辑与机器遗忘时
The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning
arXiv 2609.29045 · 2026-09-253GPP信道估计器的多智能体编排
Multi-Agent Orchestration of 3GPP Channel Estimators
arXiv 2609.29044 · 2026-09-25基于LLM链式任务规划的设计与评估：面向通用服务机器人
Design and Evaluation of LLM Chaining-Based Task Planning for General Purpose Service Robots
arXiv 2609.29043 · 2026-09-25通过Föllmer漂移的1-Wasserstein距离中的定量QSD收敛
Quantitative QSD convergence in 1-Wasserstein distance via the Föllmer drift
arXiv 2609.29042 · 2026-09-25从散乱高斯到结构化映射：基于双阶段莫顿排序的高效高斯溅射编码
From Scattered Gaussians to Structured Maps: Efficient Gaussian Splatting Coding via Dual-phase Morton Sorting
arXiv 2609.29041 · 2026-09-25神经音频水印在语音增强下的脆弱性
The Vulnerability of Neural Audio Watermarks under Speech Enhancement
arXiv 2609.29040 · 2026-09-25
