2026-08论文中文摘要
温度驱动序列建模预测有机光伏材料的年功率转换效率曲线：杜阿拉案例研究
Temperature-Driven Sequential Modeling for the Prediction of Annual Power Conversion Efficiency Profiles of Organic Photovoltaic Materials: Douala Case Study
arXiv 2608.11261 · 2026-08-13扫视、审视与思考：将视频异常检测从无训练推进到智能体推理
Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning
arXiv 2608.11260 · 2026-08-13提升K-12教育中AI辅导质量的方法
Methodologies for Improving the Quality of AI Tutoring in K-12 Education
arXiv 2608.11259 · 2026-08-13结合梯度下降的自适应混合粒子群优化算法
Adaptive Hybrid Particle Swarm Optimization with Gradient Descent
arXiv 2608.11258 · 2026-08-13基于生成树集合上不完整成对比较矩阵确定优先级向量的组合与采样方法
Combinatorial and Sampling Approaches to Determining the Priority Vector from an Incomplete Pairwise Comparison Matrix on the Set of Spanning Trees
arXiv 2608.11257 · 2026-08-13用于Cx-N2二元混合物汽液平衡预测的符号机器学习
Symbolic Machine Learning for Vapor-Liquid Equilibrium Prediction in Cx-N2 Binary Mixtures
arXiv 2608.11255 · 2026-08-13FarSky：面向生成式小时级内太阳能预测的任务感知隐空间耦合方法
FarSky: Task-Aware Latent-Space Coupling for Generative Intra-Hour Solar Forecasting
arXiv 2608.11254 · 2026-08-13解析阳光——一个社区企业
Deconstructing Sunlight - A Community Enterprise
arXiv 2608.11253 · 2026-08-13局部验证无法检测不可迁移性：智能体推理中上下文保持的上同调理论
Local verification cannot detect non-transportability: a cohomological theory of context preservation in agentic reasoning
arXiv 2608.11252 · 2026-08-13AI公平性语境下的变量选择
Variable Selection in the Context of AI Fairness
arXiv 2608.11251 · 2026-08-13AgonAlpha：通过提示经济与可扩展智能体搜索实现自主阿尔法发现
AgonAlpha: Autonomous Alpha Discovery via Prompt Economy and Scalable Agentic Search
arXiv 2608.11250 · 2026-08-13扩散到压缩：利用扩散语言模型进行无损压缩
Diffuse to Compress: Leveraging Diffusion LMs for Lossless Compression
arXiv 2608.11249 · 2026-08-13EvoGraph-Mem：面向长期语言智能体的故障感知可编辑图记忆
EvoGraph-Mem: Failure-Aware Editable Graph Memory for Long-Term Language Agents
arXiv 2608.11248 · 2026-08-13大语言模型中的从众效应缓解措施存在于单一的抵抗-接受边界上
Conformity Mitigations in Large Language Models Lie on a Single Resistance-Receptivity Frontier
arXiv 2608.11247 · 2026-08-13迈向具身智能体的管控
Towards the Harness of Embodied Agents
arXiv 2608.11246 · 2026-08-13面向在线教育中的可持续学习：一种强化学习方法
Towards Sustainable Learning in Online Education: A Reinforcement Learning Approach
arXiv 2608.11245 · 2026-08-13BEST-KAG：通过多模态知识图谱建模与大语言模型增强建筑工程标准的问答能力
BEST-KAG: Enhancing Question Answering of Building Engineering Standards with Multimodal Knowledge Graph Modeling and Large Language Model
arXiv 2608.11244 · 2026-08-13离支撑屏障：为何语义安全约束不是学习问题不变量，以及对先验设计、约束与验证的启示
The Off-Support Barrier: Why Semantic Safety Constraints Are Not Learning-Problem Invariants, and What Follows for Prior Design, Containment, and Verification
arXiv 2608.11243 · 2026-08-13在压缩中迷失：评估上下文压缩下的侧约束损失
Lost in Compaction: Evaluating Side-Constraint Loss under Context Compaction
arXiv 2608.11242 · 2026-08-13RecSys Factory：限制LLM智能体在工业推荐生命周期内的自主决策点
RecSys Factory: Bounding LLM Agent Autonomy to Decision Points in the Industrial Recommender Lifecycle
arXiv 2608.11241 · 2026-08-13VQ-bench：一种可组合的向量量化框架
VQ-bench: A Composable Vector Quantization Framework
arXiv 2608.11240 · 2026-08-13基于强化学习的数据库管理系统缓冲池自动调优以实现最优内存利用
Reinforcement Learning based DBMS Buffer Pool Auto-Tuning for Optimal Memory Utilization
arXiv 2608.11239 · 2026-08-13面向长时序偏微分方程预测的几何感知增量神经算子
Geometry-aware Incremental Neural Operator for Long-Horizon PDE prediction
arXiv 2608.11237 · 2026-08-13TRACE Bench：任务驱动的角色扮演智能体清单评估基准
TRACE Bench: Task-driven Roleplay Agentic Checklist Evaluation
arXiv 2608.11236 · 2026-08-13CORA-Diff：面向高效扩散语言模型推理的置信导向残差接受
CORA-Diff: Confidence-Oriented Residual Acceptance for Efficient Diffusion Language Model Inference
arXiv 2608.11235 · 2026-08-13将循环深度改造融入预训练语言模型：在两个参数预算下的安装、外推、迁移与保留
Retrofitting Recurrent Depth into a Pretrained Language Model: Installation, Extrapolation, Transfer, and Retention at Two Parameter Budgets
arXiv 2608.11233 · 2026-08-13Backtrader-Bench：基于自生成多项选择题的算法交易大语言模型智能体基准测试
Backtrader-Bench: Benchmarking LLM Agents on Algorithmic Trading with Self-Generated MCQs
arXiv 2608.11232 · 2026-08-13LinearKV：混合大语言模型中与位置无关缓存仅需一个缓存状态
LinearKV: One Cached State Suffices for Position-Independent Caching in Hybrid LLMs
arXiv 2608.11231 · 2026-08-13基于边的连续p-中值问题及其与物流分区的关联
The Edge-based Contiguous p-median Problem with Connections to Logistics Districting
arXiv 2608.11230 · 2026-08-13人机自主团队中基于二阶心理理论的信念同步（扩展版）
Synchronizing Beliefs with Second-Order Theory-of-Mind in Human-Autonomy Teams (Extended Version)
arXiv 2608.11229 · 2026-08-13预测激活引导的副作用
Forecasting Side Effects of Activation Steering
arXiv 2608.11227 · 2026-08-13用强化学习降低AI数据中心能耗：从单GPU到集群的大语言模型训练实测功率控制
Cutting AI Datacenter Energy with Reinforcement Learning: Measured Power Control of LLM Training from One GPU to the Fleet
arXiv 2608.11226 · 2026-08-13来自外部的身份：AI人格克隆的概念框架与研究计划
Identity from the Outside: A Conceptual Framework and Research Program for AI Personality Clones
arXiv 2608.11225 · 2026-08-13利用智能体记忆构建面向材料科学家的终身AI合作伙伴
Harnessing agent memory to build lifelong AI partners for materials scientists
arXiv 2608.11224 · 2026-08-13仅刷卡进站的公交智能卡数据的出行目的地推断：一种分层贝叶斯方法
Transit Destination Inference from Tap-In-Only Bus Smart-Card Data: A Hierarchical Bayesian Approach
arXiv 2608.11223 · 2026-08-13用于细化网络物理系统中仿真证据影响知识的概念框架
A Conceptual Framework for Refining Influence Knowledge from Simulation Evidence in Cyber-Physical Systems
arXiv 2608.11221 · 2026-08-13流程图表工程中的大语言模型：从最优工艺流程图到经验证的管道及仪表流程图
LLMs in Process Diagram Engineering: From Optimal PFDs to Validated P&IDs
arXiv 2608.11220 · 2026-08-13从整体到模块：片段级自动提示优化
From Monolithic to Modular: Segment-level Automatic Prompt Optimization
arXiv 2608.11219 · 2026-08-13MaSRead：复制潜在存储的内容寻址读取
MaSRead: Content-Addressed Reading of Replicated Latent Stores
arXiv 2608.11218 · 2026-08-13四面体的高度函数分解
Decompositions of Tetrahedra into Height Functions
arXiv 2608.11217 · 2026-08-13简易智能体建模：在笔记本电脑上模拟大型大语言模型（LLM）智能体群体
Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop
arXiv 2608.11215 · 2026-08-13对称群不可约表示的考斯特上同调
On the Coxeter Cohomology of Irreducible Representations of Symmetric Groups
arXiv 2608.11214 · 2026-08-13受扰球体的静态平衡：单谐类映射、奇偶性障碍与单单静态 regime 的已验证计数反例
Static Equilibria of Perturbed Spheres: A Single-Harmonic Class Map, a Parity Obstruction, and a Certified Counter for the Mono-Monostatic Regime
arXiv 2608.11213 · 2026-08-13检测路由翻转比知道是否修复它更容易：量化混合专家模型中由因果路由介导的损伤
Detecting a Route Flip Is Easier Than Knowing Whether to Fix It: Causal Route-Mediated Damage in Quantized Mixture-of-Experts
arXiv 2608.11212 · 2026-08-13O-度量不等式的统一解析方法及其在不动点理论中的应用
A unified analytic approach to O-metric inequalities and applications to fixed point theory
arXiv 2608.11209 · 2026-08-13用于实现协作式对话结果的多大型语言模型智能体系统的动态管控
Dynamic Governance of Multi-LLM Agent Systems for Collaborative Conversational Outcomes
arXiv 2608.11207 · 2026-08-13一种气体驱动的算法，用于求解移动沙发问题的变体
A Gas-Driven Algorithm for Variants of the Moving Sofa Problem
arXiv 2608.11206 · 2026-08-13VIScore：诊断潜在世界模型中与规划相关的质量
VIScore: Diagnosing Planning-Relevant Quality in Latent World Models
arXiv 2608.11174 · 2026-08-13格罗滕迪克常数的新上下界
New Lower and Upper Bounds for the Grothendieck Constant
arXiv 2608.11158 · 2026-08-13CausalSplat：面向3D高斯溅射的综合层级推理
CausalSplat: Towards Comprehensive Hierarchical Reasoning in 3D Gaussian Splatting
arXiv 2608.11150 · 2026-08-13
