2026-09论文中文摘要
物理智能体的安全技能退役
Safe Skill Retirement for Physical Agents
arXiv 2609.29543 · 2026-09-25非恒定曲率中极小圆盘的稳定性与唯一性
Stability and uniqueness of minimal disks in non-constant curvature
arXiv 2609.29542 · 2026-09-25当边重要性不一致时：城市道路网络上电阻排名与介数剪枝的比较
When Edge Importance Disagrees: Resistance-Ranked versus Betweenness Pruning on Urban Road Networks
arXiv 2609.29540 · 2026-09-25纯化纠缠不具有可加性
The entanglement of purification is not additive
arXiv 2609.29539 · 2026-09-25QCD相变中的有限体积非广延统计
Finite-Volume Non-extensive statistical in QCD phase
arXiv 2609.29538 · 2026-09-25E7 的次极小轨道的余切模型
A Cotangent Model for the Next-to-Minimal Orbit of E7
arXiv 2609.29537 · 2026-09-25胸部X射线设备推理的临床知识图谱
Clinical Knowledge Graphs for Chest X-Ray Device Reasoning
arXiv 2609.29536 · 2026-09-25上下文感知模糊系统中的条件聚合：纤维表示理论
Conditional Aggregation in Context-Aware Fuzzy Systems: A Fibered Representation Theory
arXiv 2609.29535 · 2026-09-25小Seifert L-空间及更多类别的三维辛化问题
The three-dimensional symplectization question for small Seifert L-spaces and further classes
arXiv 2609.29534 · 2026-09-25带演化约束的双曲平衡律的激波结构
Shock Structure for Hyperbolic Balance Laws with Evolutionary Constraints
arXiv 2609.29533 · 2026-09-25Jacobi 相位展开的超球背景，闭式表达
The ultraspherical background of the Jacobi phase expansion, in closed form
arXiv 2609.29531 · 2026-09-25时间序列验证的不可能三角：训练充分性、测试覆盖性与时间因果性之间的守恒律
The Impossible Trinity of Time-Series Validation: A Conservation Law among Training Sufficiency, Test Coverage, and Temporal Causality
arXiv 2609.29530 · 2026-09-25来自主动语音代理蜜罐的真实诈骗和垃圾电话对话语料库
A Corpus of Real Scam- and Spam-Call Conversations from an Active Voice-Agent Honeypot
arXiv 2609.29528 · 2026-09-25CoSWA-YOLOv12：疟原虫的尺度不变微小目标检测与分割
CoSWA-YOLOv12: Scale-Invariant Tiny Object Detection and Segmentation of Malaria Parasites
arXiv 2609.29527 · 2026-09-25直径为 $4$ 的图的有向直径的改进上界
An improved upper bound for oriented diameter of graphs with diameter $4$
arXiv 2609.29526 · 2026-09-25布朗核梯子的公共协方差几何与认证
Common Covariance Geometry and Certification for Brownian Kernel Ladders
arXiv 2609.29525 · 2026-09-25两阶段局部与非局部扩散系统的保结构数值格式
Structure-Preserving Numerical Schemes for Two-Stage Local and Nonlocal Dispersal Systems
arXiv 2609.29524 · 2026-09-25迈向 TabPFN 探测的病理学基础模型中可信赖的生物学对齐
Towards Trustworthy Biological Alignment in TabPFN-Probed Pathology Foundation Models
arXiv 2609.29523 · 2026-09-25陈旧并不意味着不安全：基础设施状态竞争下工具使用型LLM智能体的守卫精度
Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races
arXiv 2609.29522 · 2026-09-25Envelopt：约束凸复合优化
Envelopt: Constrained Convex Composite Optimization
arXiv 2609.29521 · 2026-09-25样本加权的端到端迹范数几何用于多任务学习
Sample-Weighted End-to-End Trace-Norm Geometry for Multitask Learning
arXiv 2609.29520 · 2026-09-25BiGraph-Diffuse：一种用于心理健康咨询的具有图结构检索的双向扩散语言模型
BiGraph-Diffuse: A Bidirectional Diffusion Language Model with Graph-Structured Retrieval For Mental Health Counseling
arXiv 2609.29519 · 2026-09-25CataOPD：用于大语言模型推理的催化式在策略蒸馏
CataOPD: Catalytic On-Policy Distillation for Large Language Model Reasoning
arXiv 2609.29518 · 2026-09-25AdaPilot：面向跨生成器文生图质量优化的场景自适应策略学习
AdaPilot: Towards Scene-Adaptive Policy Learning for Cross-Generator Text-to-Image Quality Optimization
arXiv 2609.29517 · 2026-09-25Jordan块、微分迹与Noether商环上的余理想非包含关系
Jordan Blocks, Differential Traces, and Colon-Ideal Noncontainment over Noetherian Quotients
arXiv 2609.29516 · 2026-09-25网络实现GARCH--Itô模型：高频识别下的波动率溢出
Network Realized GARCH--Itô Models: Volatility Spillovers with High-Frequency Identification
arXiv 2609.29515 · 2026-09-25物理信息神经算子代理用于二维磁流体动力学重联
Physics-Informed Neural Operator Surrogate for 2D Magnetohydrodynamic Reconnection
arXiv 2609.29514 · 2026-09-25带符号曝光：当注意力可能造成伤害时算法注意力的公平路由
Signed Exposure: Fair Routing of Algorithmic Attention When Attention Can Harm
arXiv 2609.29513 · 2026-09-25Lorentz序列空间不嵌入Lorentz函数空间
Nonembedding of Lorentz sequence spaces into Lorentz function spaces
arXiv 2609.29512 · 2026-09-25EnSiTa——面向领域特定机器翻译的三语多领域平行数据集与基准
EnSiTa - A Trilingual Multi-Domain Parallel Dataset and Benchmark for Domain-Specific Machine Translation
arXiv 2609.29511 · 2026-09-25测度与积分理论中的扩张定理作为完备性公理
Extension Theorems in Measure and Integration Theory as Completeness Axioms
arXiv 2609.29510 · 2026-09-25延迟满足作为长视界大语言模型的多智能体生存微基准：社会暴露、人格与工具使用预算
Delay-of-Gratification as a Multi-Agent Survival Micro-benchmark for Long-Horizon LLMs: Social Exposure, Personas, and Tool Use Budgets
arXiv 2609.29509 · 2026-09-25大语言模型智能体多轮一致性的评估：生存分析与失败理由分类学
Evaluation of Multi-Turn Consistency in LLM Agents: Survival Analysis and Failure-Rationale Taxonomy
arXiv 2609.29508 · 2026-09-25跨模型不动点普查能及不能仲裁关于重复的问题
What a Cross-Model Fixed-Point Census Can and Cannot Arbitrate About Repetition
arXiv 2609.29507 · 2026-09-25经典电动力学中的补偿自由源与束缚源及非辐射条件
Compensated Free and Bound Sources and Nonradiating Conditions in Classical Electrodynamics
arXiv 2609.29506 · 2026-09-25谱引导扩散：通过静态谱层调度加速推理
Spectral-Guided Diffusion: Accelerating Inference via Static Spectral Layer Scheduling
arXiv 2609.29505 · 2026-09-25PROOF：大型语言模型中对象级事实的可信度剖析
PROOF: Profiling Reliability of Object-Level Facts in Large Language Models
arXiv 2609.29504 · 2026-09-25一种用于（非）线性软化建模的微形态本构框架
A micromorphic constitutive framework for (non)linear softening modeling
arXiv 2609.29503 · 2026-09-25多尺度地震波传播的高阶梯度框架
A higher--order gradient framework for multi--scale seismic wave propagation
arXiv 2609.29502 · 2026-09-25K3曲面及超曲面的超平面截面的模映射的分歧
Ramification of the moduli map for hyperplane sections of K3s and hypersurfaces
arXiv 2609.29501 · 2026-09-25基于图的Stackelberg安全博弈用于可信6G解构架构
A Graph-Based Stackelberg Security Game for Trustworthy 6G Disaggregated Architecture
arXiv 2609.29500 · 2026-09-25任务感知频谱剪枝：一种用于高效大语言模型推理的掩码混合框架
Task-Aware Spectral Pruning: A Mixture-of-Masks Framework for Efficient LLM Inference
arXiv 2609.29499 · 2026-09-25Aliprantis关于局部实心拓扑的问题
Aliprantis's questions on locally solid topologies
arXiv 2609.29498 · 2026-09-25通过生成顺序干预评估解释驱动的视觉-语言推理
Evaluating Explanation-Driven Vision-Language Reasoning via Generation Order Interventions
arXiv 2609.29496 · 2026-09-25MOND 是复杂暗物质扇区的涌现有效定律吗？
Is MOND an Emergent Effective Law of a Complex Dark Matter Sector?
arXiv 2609.29495 · 2026-09-25谁把“我”放进了人工智能？机器自我报告的证据来源与可采性
Who Put the I in AI? Provenance and the Admissibility of Machine Self-Report
arXiv 2609.29494 · 2026-09-25每个图最终都是Turán-优的和Turán-稳定的
Every graph is eventually Turán-good and Turán-stable
arXiv 2609.29493 · 2026-09-25QEVOLVE-Bench：量子SDK演进与修复规划的基础基准
QEVOLVE-Bench: A Seed Benchmark for Quantum SDK Evolution and Repair Planning
arXiv 2609.29492 · 2026-09-25具有可证明最优性的体素软体机器人生成式进化设计
Generative Evolutionary Design of Voxel-Based Soft Robots with Provable Optimality
arXiv 2609.29491 · 2026-09-25RoboLDA：一种用于揭示体素软机器人具身层次结构的概率生成模型
RoboLDA: A Probabilistic Generative Model for Uncovering Embodied Hierarchical Structures in Voxel-based Soft Robots
arXiv 2609.29490 · 2026-09-25
