2026-08论文中文摘要
基于任务感知多阶段大语言模型（LLM）模拟来访者的动机访谈咨询师评估
Evaluation of Motivational Interviewing Counsellors with Task-Aware Multi-Stage LLM-Based Simulated Clients
arXiv 2608.07499 · 2026-08-11了解你就是一切：LLM智能体在社交媒体模拟中实现近乎完美的个人资料一致反应预测
Knowing You Is Everything: LLM Agents Achieve Near-Perfect Profile-Consistent Reaction Prediction in Social Media Simulation
arXiv 2608.07498 · 2026-08-11EvalConvoLearn：一个用于评估辅导对话中具身学习者模拟的开源框架
EvalConvoLearn: An Open-Source Framework for Evaluating Grounded Learner Simulations in Tutoring Conversations
arXiv 2608.07497 · 2026-08-11人机模拟交互：面向政策的大语言模型智能体模拟中从预测到探索
Human-Simulation Interaction: From Prediction to Exploration in LLM Agent Simulations for Policy
arXiv 2608.07496 · 2026-08-11EmoPatient：用于姑息治疗沟通训练的情绪导向患者模拟器
EmoPatient: An Emotion-Directed Patient Simulator for Realistic Palliative Care Communication Training
arXiv 2608.07495 · 2026-08-11如何向AI提问：大型语言模型提示工程的用户视角调查
How to Ask the AI: A User Perspective Survey for Large Language Model Prompting
arXiv 2608.07494 · 2026-08-11透明度陷阱：AI免责声明如何在高风险决策中引发过度自信
The Transparency Trap: How AI Disclaimers Create Overconfidence in High-Stakes Decisions
arXiv 2608.07493 · 2026-08-11前端本体论工具可用性的初步评估
Initial Evaluation of the Usability of Front-End Ontology Tooling
arXiv 2608.07491 · 2026-08-11经验敏感型游戏学习：人类与语言智能体的行为研究
Experience-Sensitive Game Learning: A Behavioral Study of Humans and Language Agents
arXiv 2608.07490 · 2026-08-11从街景图像揭示人类大五人格特质与建成环境特征之间的关联
Uncovering the Associations between Human Big Five Personality Traits and Built Environment Characteristics from Street View Imagery
arXiv 2608.07489 · 2026-08-11大型语言模型（LLM）比专家自身更擅长解释专家
Large Language Models Explain Experts Better Than Experts Themselves
arXiv 2608.07488 · 2026-08-11SafeStudent驾驶：一种基于计算机视觉与移动感知的多模态驾驶员安全系统，用于支持青少年驾驶员
SafeStudent Driving: A Multimodal Driver-Safety System to Support Teen Drivers Using Computer Vision and Mobile Sensing
arXiv 2608.07487 · 2026-08-11一种用于晕动症潜在原因估计的符号机器学习方法
A Symbolic Machine Learning Approach for Cybersickness Potential-Cause Estimation
arXiv 2608.07486 · 2026-08-11作为抵抗的幽默：通过基于幽默的创意实践使AI的环境与社会影响具象化
Humour as Resistance: Visceralizing the Environmental and Social Impact of AI through Humour-based Creative Practices
arXiv 2608.07485 · 2026-08-11利用游戏玩法和用户数据预测及识别VR游戏中晕动症（CS）表现的原因
Using the gameplay and user data to predict and identify causes of cybersickness manifestation in virtual reality games
arXiv 2608.07484 · 2026-08-11生成式AI作为以人为本设计的支持，而非替代
Generative AI as Support, Not Replacement, in Human-Centered Design
arXiv 2608.07483 · 2026-08-11从以用户为中心的设计到人机协作：人机交互的未来为何仍以人作为起点
From Human-Centered Design to Human-AI Collaboration: Why the Future of HCI Still Starts With People
arXiv 2608.07482 · 2026-08-11基于《反人类牌》的跨模型幽默偏好建模
Cross-Model Humor Preference Modeling with Cards Against Humanity
arXiv 2608.07481 · 2026-08-11人类驾驶主动推理模型中的情感
Emotion in an active inference model of human driving
arXiv 2608.07480 · 2026-08-11PragyaDoc：低资源场景下多语种医学文档理解的通用文档智能框架
PragyaDoc: A Universal Document Intelligence Framework for Multilingual Medical Document Understanding in Low-Resource Settings
arXiv 2608.07478 · 2026-08-11面向伦理人工智能的设计：用于人力资源的自动机器学习（AutoML）中提升公平性与用户体验的人机交互（HCI）功能考量
Designing for Ethical AI: HCI Feature Considerations to Improve Fairness and User Experience in AutoML use for Human Resources
arXiv 2608.07477 · 2026-08-11结构理论中的确定化：基于闭包、可比性与联合可容许性的统一框架
Determinization in Structure Theories: A Unified Framework via Closure, Comparability, and Joint Admissibility
arXiv 2608.07476 · 2026-08-11在STEM评估中定位生成式人工智能：何时要求、搭建支架或限制其使用
Positioning Generative Artificial Intelligence in STEM Assessment: When to Require, Scaffold, or Restrict Its Use
arXiv 2608.07475 · 2026-08-11面向评估型人工智能的论辩基础
Towards an Argumentative Foundation for Evaluative AI
arXiv 2608.07473 · 2026-08-11用于改进短期野火预测的数据驱动火区分割方法
Data-Driven Fire-Zone Segmentation for Improved Short-Term Wildfire Prediction
arXiv 2608.07472 · 2026-08-11人工智能在银行欺诈操作识别中的应用
Application of Artificial Intelligence for Fraudulent Banking Operations Recognition
arXiv 2608.07471 · 2026-08-11TEPA：撤销过时记忆以构建冲突鲁棒的语言智能体
TEPA: Revoking Stale Memories for Conflict-Robust Language Agents
arXiv 2608.07429 · 2026-08-11CoBa：通过计算均衡路由实现高性价比的测试时扩展
CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing
arXiv 2608.07424 · 2026-08-11高纵横比硅纳米棒的光机械悬浮与控制
Optomechanical Levitation and Control of High Aspect Ratio Silicon Nanorods
arXiv 2608.07415 · 2026-08-11关于同步性的最优拉普拉斯若尔当结构
On the Optimal Laplacian Jordan Structure for Synchronizability
arXiv 2608.07286 · 2026-08-11SCALE：基于大语言模型与嵌入的科学概念聚合，用于细粒度分类体系扩展
SCALE: Scientific Concept Aggregation via LLMs and Embeddings for Fine-Grained Taxonomy Extension
arXiv 2608.07254 · 2026-08-11指数最后通行渗流中Busemann函数的负相关性
Negative association of Busemann functions in exponential last-passage percolation
arXiv 2608.07236 · 2026-08-11面向恶劣天气去除的退化感知跨模态补偿提示学习
Degradation-Aware Prompt Learning with Cross-Modal Compensation for Adverse Weather Removal
arXiv 2608.06939 · 2026-08-11RibAssist 3D：基于CT衍生投影的双侧肋骨骨折检测、配对与选择性3D定位
RibAssist 3D: Biplanar Rib-Fracture Detection, Addressing, and Selective 3D Localization from CT-Derived Projections
arXiv 2608.06914 · 2026-08-11无序地标视觉导航
Unordered Landmark Visual Navigation
arXiv 2608.06833 · 2026-08-11t-相交族的谱希尔顿-米尔纳-弗兰克尔定理
A Spectral Hilton--Milner--Frankl Theorem for $t$-Intersecting Families
arXiv 2608.06810 · 2026-08-11bioMoR：面向有效基因组学习的生物学引导递归混合模型
bioMoR: Biology-Guided Mixture-of-Recursions for Effective Genomic Learning
arXiv 2608.06727 · 2026-08-11面向对称矩阵变量数据的贝叶斯高斯混合建模
Bayesian Gaussian Mixture Modeling for Symmetric Matrix Variate Data
arXiv 2608.06658 · 2026-08-11建模相对于估计性能包络的运动员衰老
Modelling Athletic Ageing Relative to an Estimated Performance Envelope
arXiv 2608.06635 · 2026-08-11自动化项目评估：利用大语言模型生成的评语预测项目的接受与拒绝
Automated item evaluation: Predicting item acceptance and rejection using LLM-generated critiques
arXiv 2608.06609 · 2026-08-11三维聚焦能量临界广义Hartree方程的散射准则
Scattering Criteria for the Three-Dimensional Focusing Energy-Critical Generalized Hartree Equation
arXiv 2608.06498 · 2026-08-11两阶段相位型队列：闭式分布与BuTools的数值精度格局
Two-Phase Phase-Type Queues: Closed-Form Distributions, Sensitivity Analysis and the Boundary of Algebraic Tractability
arXiv 2608.06414 · 2026-08-11ω-0：一种用于类人机器人协同移动操作的潜在预测世界动作模型
$ω$-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation
arXiv 2608.06375 · 2026-08-11突破量子控制系统中的内存瓶颈，实现更精确的实验与更高吞吐量的计算
Breaking Memory Bottlenecks in Quantum Control Systems for More Precise Experiments and Higher Throughput Computing
arXiv 2608.06318 · 2026-08-11无任何监督的在线策略自蒸馏
On-Policy Self-Distillation without Any Supervision
arXiv 2608.06296 · 2026-08-11MASS：具有权威共享状态的多人世界模型
MASS: Multiplayer World Models with Authoritative Shared State
arXiv 2608.06257 · 2026-08-11面向可部署的孟加拉语手语识别：基于专家验证数据与轻量型注意力模型
Toward Deployable Bangla Sign Language Recognition with Expert-Validated Data and a Lightweight Attention-Based Model
arXiv 2608.06252 · 2026-08-11Poli-Bias：理解与测量大型语言模型在国际政治冲突中的偏差
Poli-Bias: Understanding and Measuring Large Language Model Biases in International Political Conflicts
arXiv 2608.06123 · 2026-08-11Wan-Animate-2：拓展角色动画的应用边界
Wan-Animate-2: Pushing the Application Boundaries of Character Animation
arXiv 2608.06009 · 2026-08-11四维φ⁴模型非微扰二阶平均场理论中的平凡性
Triviality in a Non-Perturbative Second-Order Mean-Field Theory for $ϕ^4_4$
arXiv 2608.05998 · 2026-08-11
