2026-09论文中文摘要
智能体应在何时以及如何澄清？CIGAsk：通过反事实信息增益教LLM进行澄清
When and How Should an Agent Clarify? CIGAsk: Teaching LLMs to Clarify via Counterfactual Information Gain
arXiv 2609.24290 · 2026-09-22TTSE：一种双轨在线自进化框架
TTSE: A Two-Track Online Self-Evolution Framework
arXiv 2609.24289 · 2026-09-22电路-架构-训练协同设计：基于再生型SA相似性感知的模拟存内计算激进SAR跳变
Circuit-Architecture-Training Co-Design with Regenerative-SA Similarity Sensing for Aggressive SAR Skipping in Analog Compute-in-Memory
arXiv 2609.24288 · 2026-09-22流匹配中的无分类器引导：非自治势、过冲与后验均值控制
Classifier-Free Guidance in Flow Matching: Non-Autonomous Potentials, Overshoot, and Posterior-Mean Control
arXiv 2609.24287 · 2026-09-22孤立中子星系统的旋转射电瞬变相与中心致密天体后裔
Rotating Radio Transient Phases of Isolated Neutron Star Systems and Descendants of Central Compact Objects
arXiv 2609.24286 · 2026-09-22分子云中气相元素丰度（GEMS）第十二：前恒星核c-C3D2邻对位比率的首次探究
Gas phase Elemental abundances in Molecular cloudS (GEMS) XII. First look into the para-to-ortho ratio of c-C3D2 towards prestellar cores
arXiv 2609.24285 · 2026-09-22量子多体框架用于被动标量湍流
Quantum many-body framework for passive-scalar turbulence
arXiv 2609.24284 · 2026-09-22量子计算求解相对论标量束缚态的Bethe-Salpeter方程：基于张量网络VQE
Quantum Computing Solution of the Bethe-Salpeter Equation for Relativistic Scalar Bound States via Tensor-Network VQE
arXiv 2609.24282 · 2026-09-22压缩氧化铁中电子熵驱动的相变
Electronic-Entropy-Driven Phase Transitions in Compressed Iron Oxides
arXiv 2609.24281 · 2026-09-22用于恶意软件检测的控制流图神经网络的时间泛化与解释稳定性
Temporal Generalization and Explanation Stability of Control Flow Graph Neural Networks for Malware Detection
arXiv 2609.24280 · 2026-09-22大规模三圈形状因子的完整技术：胶子情形
Holonomic techniques for massive 3-loop form factors: the gluonic case
arXiv 2609.24279 · 2026-09-22高维在线变点检测：自适应阈值与可解释性
High-Dimensional Online Change Point Detection with Adaptive Thresholding and Interpretability
arXiv 2609.24278 · 2026-09-22一个数字值多少像素？用于GUI智能体置信度估计的位置感知坐标熵
How Many Pixels Is a Digit Worth? Place-Aware Coordinate Entropy for GUI Agent Confidence Estimation
arXiv 2609.24277 · 2026-09-22双曲视觉-语言模型的层级提示学习
Hierarchical Prompt Learning for Hyperbolic Vision-Language Models
arXiv 2609.24276 · 2026-09-22采样之前先看结构：面向数据高效文本转语音的社区感知核心集选择
Structure Before Sampling: Community-Aware Core-Set Selection for Data-Efficient Text-to-Speech
arXiv 2609.24275 · 2026-09-22vla.simd：面向语言条件操控的高效CPU推理
vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation
arXiv 2609.24274 · 2026-09-22半经典引力中带迹反常的旋转黑洞周围Novikov-Thorne吸积盘的特征
Signatures of Novikov-Thorne accretion disks around rotating black holes in semiclassical gravity with trace anomaly
arXiv 2609.24273 · 2026-09-22常数硬币完全信息辩论系统：$\mathsf{P}$ 类语言具有任意小强错误的判定
Constant-Coin Complete-Information Debates for $\mathsf{P}$ with Arbitrarily Small Strong Error
arXiv 2609.24272 · 2026-09-22剖析芯片缩放如何打破GPU细粒度调度
Dissecting How Die Scaling Breaks GPU Fine-grained Scheduling
arXiv 2609.24270 · 2026-09-22高阶间断伽辽金方法的一种子单元细化熵残差驱动限制策略
A subcell-refined entropy-residual-driven limiting strategy for high-order discontinuous Galerkin methods
arXiv 2609.24268 · 2026-09-22StreamTN：面向对话系统中流式TTS的低延迟中文文本规范化模型
StreamTN: A Low-Latency Streaming Chinese Text Normalization Model for Streaming TTS in Dialogue Systems
arXiv 2609.24267 · 2026-09-22基于QSVT的量子Jacobi算法用于线性方程组求解及其在Poisson方程中的应用
A QSVT-Based Quantum Jacobi Algorithm for Linear Systems with Application to the Poisson Equation
arXiv 2609.24266 · 2026-09-22无监督脑部异常检测：基于扩散先验的贝叶斯逆问题
Unsupervised Brain Anomaly Detection as a Bayesian Inverse Problem with Diffusion Prior
arXiv 2609.24265 · 2026-09-22规范程序性动作：工具使用智能体轨迹的可审计标注协议
Canonical Procedural Actions: An Auditable Annotation Protocol for Tool-Use Agent Traces
arXiv 2609.24264 · 2026-09-22学习在6G in-X子网络中最大化能量效率
Learning to Maximize Energy Efficiency in 6G in-X Subnetworks
arXiv 2609.24263 · 2026-09-22考虑故障响应与节点电压一致性的含分布式可再生能源负荷侧系统等效建模
Equivalent Modeling of Load-Side Systems With Distributed Renewable Generation Considering Fault Responses and Nodal Voltage Coherence
arXiv 2609.24262 · 2026-09-22Landau解在旋转自相似类中的刚性
Rigidity of Landau solution in the rotated self-similar class
arXiv 2609.24261 · 2026-09-22具有最优VC率的对抗鲁棒PAC学习
Adversarially Robust PAC Learning with Optimal VC Rates
arXiv 2609.24260 · 2026-09-22加权Bergman核的参数依赖性：超越光滑性
Parameter Dependence of Weighted Bergman Kernels Beyond Smoothness
arXiv 2609.24258 · 2026-09-22一种通过混合分裂形式微分算子和广义熵投影的离散熵守恒/稳定通量重构格式
A Discretely Entropy Conserving/Stable Flux Reconstruction Scheme via Hybridized Split Form Differential Operator and Generalized Entropy Projection
arXiv 2609.24257 · 2026-09-22托卡马克磁场约束下对等离子体中的测地声模
Geodesic Acoustic Modes in pair plasmas confined in tokamak magnetic fields
arXiv 2609.24256 · 2026-09-22Selberg筛权重与Kloosterman和的符号变化. II. 至多四个素因子的无平方因子模
Selberg sieve weights and sign changes of Kloosterman sums. II. Square-free moduli with at most four prime factors
arXiv 2609.24255 · 2026-09-22使碎片化报告变得可读：发现孟加拉国性暴力的模式与认知
Making Fragmented Reports Legible: Finding Patterns and Perceptions of Sexual Violence in Bangladesh
arXiv 2609.24254 · 2026-09-22OpenFlyScan：面向消费级无人机的质量引导航拍重建系统
OpenFlyScan: A Quality-Guided Aerial Reconstruction System for Consumer Drones
arXiv 2609.24253 · 2026-09-22Lean中的Iris
Iris in Lean
arXiv 2609.24252 · 2026-09-22$\R^4_+$ 中稳定的毛细极小超曲面
Stable Capillary Minimal Hypersurfaces in $\R^4_+$
arXiv 2609.24251 · 2026-09-22强化学习启发的黑盒对抗攻击用于计算机视觉
Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision
arXiv 2609.24249 · 2026-09-22Selberg筛权重与Kloosterman和的符号变化. I. 平移权重的均匀渐近
Selberg sieve weights and sign changes of Kloosterman sums. I. Uniform asymptotics for shifted weights
arXiv 2609.24248 · 2026-09-22玻色玻璃的热演化与无序依赖性：空间、谱及局域化特征
Thermal Evolution and Disorder Dependence of the Bose-glass: Spatial, Spectral, and Localization Signatures
arXiv 2609.24247 · 2026-09-22Taramandal-GPT：利用知识检索与结构化思维提升天体动力学问题求解能力
Taramandal-GPT: Enhancing Astrodynamics Problem-Solving with Knowledge Retrieval and Structured Thinking
arXiv 2609.24246 · 2026-09-22AI辅助的特殊教育社会故事干预：AdaptED Stories的设计
AI-Assisted Social Story Intervention for Special Education: The Design of AdaptED Stories
arXiv 2609.24245 · 2026-09-22看关键之处：面向细粒度视觉-语言推理的免费、无标签视觉证据信号
Look Where It Counts: A Free, Label-Free Visual Evidence Signal for Fine-Grained Vision-Language Reasoning
arXiv 2609.24244 · 2026-09-22驯服视觉语言模型中的思维链混淆：从机制证据到激活强制执行
Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation Enforcement
arXiv 2609.24243 · 2026-09-22智能体AI的预期性人类监督：一种哲学解释
Anticipatory Human Oversight of Agentic AI: A Philosophical Account
arXiv 2609.24242 · 2026-09-22Hessian 秩约束用于非线性潜变量模型的结构学习
Hessian Rank Constraint for Learning Structure of Nonlinear Latent Variable Models
arXiv 2609.24241 · 2026-09-22与持续射电源相关的快速射电暴偏好贫氢超亮超新星宿主环境
Fast Radio Bursts Associated with Persistent Radio Sources Prefer Hydrogen-poor Superluminous Supernova Host Environments
arXiv 2609.24240 · 2026-09-22最优Ferrers图秩度量码：新构造、图组合及其在常维子空间码中的应用
Optimal Ferrers Diagram Rank-Metric Codes: New Constructions, Diagram Combinations, and Applications to Constant-Dimension Subspace Codes
arXiv 2609.24239 · 2026-09-22记忆 vs. 上下文？语言模型中事实回忆的影响因素
Memory vs. Context? Influential Factors of Factual Recall in Language Models
arXiv 2609.24238 · 2026-09-22pO、OO和Ne--Ne碰撞中的喷注状双强子关联
Jet-like di-hadron correlations in pO, OO, and Ne--Ne collisions
arXiv 2609.24237 · 2026-09-22知识图谱内容嵌入中的高效稠密向量检索
Efficient Dense Vector Search within Knowledge Graph Content Embeddings
arXiv 2609.24236 · 2026-09-22
