2026-08论文中文摘要
PlayWorld：基于智能体玩家的长程目标世界模型基准测试
PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives
arXiv 2608.13552 · 2026-08-17基于交叉注意力潜在稀疏专家的细粒度动作识别
Fine-Grained Action Recognition with Cross-Attentive Latent Sparse Experts
arXiv 2608.13458 · 2026-08-17修复会破坏安全性吗？对迭代式大语言模型驱动的基础设施即代码修复中安全性退化的实证研究
Does Fixing Break Security? An Empirical Study of Security Degradation in Iterative LLM-Driven Infrastructure-as-Code Repair
arXiv 2608.13404 · 2026-08-17朗兰兹对偶与不变微分算子：SL(2n+1)的情形
Langlands Duality and Invariant Differential Operators: the Case SL(2n+1)
arXiv 2608.13400 · 2026-08-17通过自相关约束的逆设计实现光谱平滑的宽带响应
Spectrally smooth broadband response via autocorrelation-constrained inverse design
arXiv 2608.13367 · 2026-08-17具有对数势的自旋玻璃中的老化现象
Aging in a spin glass with logarithmic correlations
arXiv 2608.13361 · 2026-08-17面向红外光谱化学传感与分析的仿真到真实迁移学习：从分子到复杂样品
Simulation-to-real transfer learning for infrared spectroscopic chemical sensing and analysis from molecules to complex samples
arXiv 2608.13341 · 2026-08-17本征态热化的相变：通过AGT对应实现的禁戒奇点与瞬子增殖
Phase transition from eigenstate thermalization: forbidden singularity and instanton proliferation via AGT correspondence
arXiv 2608.13246 · 2026-08-17评估近距双星系统中的行星稳定性与长期宜居性：70 Oph、36 Oph、γ Leo
Assessing Planetary Stability and Long-Term Habitability in Nearby Stellar Binaries: 70 Oph, 36 Oph, $γ$ Leo
arXiv 2608.13243 · 2026-08-17从四重简单分支覆盖表示重构Turaev--Viro不变量
Reconstructing Turaev-Viro Invariants from Four-Fold Simple Branched Covering Presentations
arXiv 2608.13241 · 2026-08-17GEM：一种连接推理与检索的生成式嵌入模型
GEM: A Generative Embedding Model Bridging Reasoning and Retrieval
arXiv 2608.13200 · 2026-08-17本征态热化系统中相变的Lee-Yang范式
Lee-Yang paradigm of phase transition in eigenstate thermalized systems
arXiv 2608.13174 · 2026-08-17Wishart矩阵与变形GOE矩阵的极端主子式
Extreme principal minors of Wishart and deformed GOE matrices
arXiv 2608.13154 · 2026-08-17HBF在大语言模型（LLM）服务系统中的潜在应用
Potential Applications of HBF in LLM Serving Systems
arXiv 2608.13127 · 2026-08-17TEMPO：面向内存密集型与计算密集型场景的感知完成时间的专家并行负载均衡
TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Regimes
arXiv 2608.13057 · 2026-08-17基于推理时无梯度优化的空间接地文本到视频生成
Spatially-Grounded Text-to-Video Generation via Inference-Time Gradient-Free Optimization
arXiv 2608.13037 · 2026-08-17InterSAGE：面向智能体互联网的安全可互操作且可验证的协议
InterSAGE: The Secure and Verifiable Interoperability Protocol for An Internet of Agents
arXiv 2608.13030 · 2026-08-17分布强化学习中分位数时间差分学习的在线推断
Online Inference for Quantile Temporal Difference Learning in Distributional Reinforcement Learning
arXiv 2608.12973 · 2026-08-17步态过程中额状面与横断面上的脊柱耦合：胸椎与腰椎的节段性及时间依赖性分析
Spinal Coupling in Frontal and Transversal Plane During Gait - A Segmental and Time-Dependent Analysis of the Thoracic and Lumbar Spine
arXiv 2608.12945 · 2026-08-17通过因果推理发现基于大语言模型的多智能体系统的高效且可解释的通信拓扑
Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference
arXiv 2608.12921 · 2026-08-17预测性记忆定位：从内部信号预测选择性干预路径
Predictive Memory Localization: Forecasting Selective Intervention Paths from Internal Signals
arXiv 2608.12892 · 2026-08-17Hayman-Wu常数为π²
The Hayman--Wu constant is $π^2$
arXiv 2608.12844 · 2026-08-17快速A/B/n测试：通过树耦合反馈共享实现精确多策略比较
Fast A/B/n Testing: Exact Multi-Policy Comparison via Tree-Coupled Feedback Sharing
arXiv 2608.12831 · 2026-08-17在可视化与人机交互（HCI）研究中考虑贡献声明
Considering Contribution Statements in Visualization and HCI Research
arXiv 2608.12792 · 2026-08-17SynAct：用于自适应综合优化的推理-行动大语言模型智能体
SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization
arXiv 2608.12751 · 2026-08-17量子去噪器中的奇偶基底：固定映射去噪网络的闭式基准
Parity Floors in Quantum Denoisers: A Closed-Form Benchmark for Fixed-Map Denoising Networks
arXiv 2608.12712 · 2026-08-17在B⁺→K⁺π⁺π⁻衰变中观测到多个CP破坏源
Observation of several sources of $C\!P$ violation in $B^+ \!\to K^+ π^+ π^-$ decays
arXiv 2608.12614 · 2026-08-17$B^+ \to K^+ π^+ π^-$衰变中未解决谜题的解析
Resolution of outstanding puzzles in $B^+ \!\to K^+ π^+ π^-$ decays
arXiv 2608.12613 · 2026-08-17B⁺→K⁺π⁺π⁻衰变的振幅分析
Amplitude analysis of $B^+ \!\to K^+ π^+ π^-$ decays
arXiv 2608.12612 · 2026-08-17波的最大亮度定理
Maximum brightness theorem for waves
arXiv 2608.12578 · 2026-08-1763维Borsuk问题的一个AI生成反例
An AI Generated Counterexample to Borsuk Problem in Dimension 63
arXiv 2608.12561 · 2026-08-17人工智能驱动的多场景利率预测：银行资产管理的概念验证
AI-Driven Multiscenario Interest Rate Forecasting: A Proof of Concept for Banking Asset Management
arXiv 2608.12424 · 2026-08-17Zwanziger 视界函数的盲区
Blind Spots of the Zwanziger Horizon Function
arXiv 2608.12413 · 2026-08-17FAA国家野生动物撞击数据库（1990-2026）的开放版本聚合数据：按动物科、机身和机场划分的条件损伤率
Open versioned aggregates of the FAA National Wildlife Strike Database (1990-2026): conditional damage rates by animal family, airframe, and airport
arXiv 2608.12390 · 2026-08-17黑洞到白洞爆炸的同步辐射与逆康普顿特征：星际介质中Weibel介导的外部激波
Synchrotron and Inverse-Compton Signatures of Black to White Hole Explosions: Weibel-Mediated External Shocks in the Interstellar Medium
arXiv 2608.12380 · 2026-08-17StreamReason-Bench：大型语言模型能否推理事件时间流处理语义？
Can Large Language Models Reason about Event-Time Stream-Processing Semantics?
arXiv 2608.12348 · 2026-08-17大语言模型通过了历史考试却遗漏了《历史》：波兰高中毕业考试Matura基准测试
Lost in Historical Time? A Polish History Matura Benchmark for Large Language Models
arXiv 2608.12343 · 2026-08-17可解释计算机视觉中的类别激活映射：CNN、Transformer及基础模型时代视觉解释的以方法为中心的综述
Class Activation Mapping in Explainable Computer Vision: A Method-Centered Review of CNN, Transformer, and Foundation-Model-Era Visual Explanations
arXiv 2608.12299 · 2026-08-17生化计算模块的收敛速率下界
On the Convergence Rate Lower Bound of Biochemical Computational Modules
arXiv 2608.12109 · 2026-08-17高围长图的${\rm b}^*$-着色与$z$-着色
On ${\rm b}^{\ast}$-Coloring and $z$-Coloring of graphs with high girth
arXiv 2608.12069 · 2026-08-17作为广域灾害信息基础设施的中波调幅广播的灾害信息可达性：2024年能登半岛地震的教训
Disaster Information Reachability of Medium-Wave AM Broadcasting as a Wide-Area Disaster Information Infrastructure: Lessons from the 2024 Noto Peninsula Earthquake
arXiv 2608.11925 · 2026-08-17基于时序负知识迁移的抗捷径蒸馏
Anti-Shortcut Distillation via Temporal Negative Knowledge Transfer
arXiv 2608.11789 · 2026-08-17规格表并非内核：对NVIDIA Blackwell Ultra上INT8可用性的ISA与源代码级审计
Spec Sheets Are Not Kernels: An ISA- and Source-Level Audit of INT8 Availability on NVIDIA Blackwell Ultra
arXiv 2608.11693 · 2026-08-17让AI生成的反馈发挥作用：从提供到学生执行
Making AI-Generated Feedback Matter: A Large-Scale Study of Feedback Workflows and Student Enactment
arXiv 2608.11625 · 2026-08-17由公共包层演化产生的氦壳燃烧蓝水平分支星
A Helium-shell Burning Blue Horizontal Branch Star Produced from Common Envelope Evolution
arXiv 2608.11557 · 2026-08-17收敛是不可避免的吗？将输出同质性追溯至基础模型
Is Convergence Inevitable? Tracing Output Homogeneity Back to Base Models
arXiv 2608.11426 · 2026-08-17中间氧空穴态的多体失稳
Many-Body Destabilization of Intermediate Oxygen-Hole States
arXiv 2608.11388 · 2026-08-17格罗滕迪克常数的长周期AI研究：人机数学协作的案例研究
Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration
arXiv 2608.11195 · 2026-08-17用于真三维重力反演的谱域伪逆方法
A Spectral-Domain Pseudo-Inverse Method for True 3D Gravity Inversion
arXiv 2608.11014 · 2026-08-17基于等离子体纳米管的单个活细胞电透化动力学的SERS研究
SERS study of single-live-cell electrical permeabilization dynamics via plasmonic nanotubes
arXiv 2608.10924 · 2026-08-17
