2026-09论文中文摘要
所罗门诺夫归纳法与奇异积分
Solomonoff Induction and Singular Integrals
arXiv 2609.01666 · 2026-09-03折叠代数拟阵：特征刚性与几乎熵分离
Folded-Algebraic Matroids: Characteristic Rigidity and Almost-Entropic Separation
arXiv 2609.01664 · 2026-09-03无需越狱的上下文推断攻击
Context Inference Attacks Without Jailbreaks
arXiv 2609.01663 · 2026-09-03经济增长理论中的同时同调性与双哈密顿结构
Simultaneous Holotheticity and Bi-Hamiltonian Structures in Economic Growth Theory
arXiv 2609.01661 · 2026-09-03智能体多快会“退化”？面向生产决策的大语言模型（LLM）智能体长时程退化的实证研究
How Fast Do Agents Rot? An Empirical Study of Long-Horizon Degradation in LLM Agents for Production Decision-Making
arXiv 2609.01660 · 2026-09-03超越文本思维链：自动驾驶中基于动作的推理综述
Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving
arXiv 2609.01659 · 2026-09-03PRO-Step：用于检索增强生成的步骤级过程奖励优化
PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation
arXiv 2609.01658 · 2026-09-03NeoMME：用于高效微调与推理的单塔多模态原生多语言基础编码器
NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference
arXiv 2609.01657 · 2026-09-03用于多元正态数据的正态-逆Wishart（NIW）贝叶斯合成器及其在多基因风险评分中的应用
A normal-inverse-Wishart (NIW) Bayesian synthesizer for multivariate normal data with application to polygenic risk scores
arXiv 2609.01656 · 2026-09-03从特征交互到特征迁移：面向可扩展推荐模型的统一模块
From Feature Interaction to Feature Transport - A Unified Block for Scalable Recommendation Models
arXiv 2609.01655 · 2026-09-03MELON：用于多事件文本到长视频检索的大规模数据集
MELON: A Large-Scale Dataset for Multi-Event Text-to-Long-Video Retrieval
arXiv 2609.01654 · 2026-09-03结合知识图谱与生成式AI中检索增强生成技术提升临床决策支持与鉴别诊断
Enhancing Clinical Decision Support and Differential Diagnosis with Knowledge Graphs, and Retrieval Augmented Generation in Generative AI
arXiv 2609.01653 · 2026-09-03并非所有匹配都具有同等价值：求职匹配平台中以留存为核心的推荐在线实验
Not All Matches Are Equally Valuable: An Online Experiment of Retention-Focused Recommendation in a Job-Matching Platform
arXiv 2609.01652 · 2026-09-03基于统计特征的慢特征分析对非平稳未知过程的参数推断
Parameter inference from a non-stationary unknown process using statistical feature-based slow feature analysis
arXiv 2609.01651 · 2026-09-03f(Q)引力中的晚期暗能量动力学：一项数据驱动分析
Late-time dark energy dynamics in $f(Q)$ gravity: A data-driven analysis
arXiv 2609.01650 · 2026-09-03一种用于直播平台协同异常行为早期检测的数据驱动多模态方法
A Data-Driven Multimodal Method for Early Detection of Coordinated Abnormal Behaviors in Live-Streaming Platforms
arXiv 2609.01649 · 2026-09-03Python中用于相关矩阵与协方差矩阵预测的矩阵感知真评分规则及显著性检验
Matrix-Aware Proper Scoring Rules and Significance Testing for Correlation and Covariance Forecasts in Python
arXiv 2609.01648 · 2026-09-03面向WASP-2025共享任务的基于SciBERT的高效上下文受限望远镜文献分类
Efficient Context-Limited Telescope Bibliography Classification for the WASP-2025 Shared Task Using SciBERT
arXiv 2609.01647 · 2026-09-03玻色-爱因斯坦凝聚暗星的参数空间、真实物质与普适关系
Parameter Space, Realistic Matter, and Universal Relations in Bose--Einstein Condensate Dark Stars
arXiv 2609.01646 · 2026-09-03词汇差距即公平差距：公共福利获取检索系统中的语域不匹配
The Vocabulary Gap Is an Equity Gap: Register Mismatch in Retrieval Systems for Public-Benefits Access
arXiv 2609.01645 · 2026-09-03自作用力问题的统一处理
A Unified Treatment of the Self-Force Problem
arXiv 2609.01644 · 2026-09-03五棱柱骰子投掷的概率模型
A Probability Model for Pentagonal Prism Dice Rolls
arXiv 2609.01643 · 2026-09-03检索前想象：面向大语言模型智能体的前瞻技能检索
Imagine Before Retrieval: Prospective Skill Retrieval for LLM Agents
arXiv 2609.01642 · 2026-09-03动态属性图中结构行为分析的新型信息工作流
A Novel Information Workflow for Structural Behavioural Analysis in Dynamic Attributed Graphs
arXiv 2609.01640 · 2026-09-03关系中社会互动的逆向规划
Inverse planning of social interactions in relationships
arXiv 2609.01639 · 2026-09-03使用稳定平衡权重对多个估计量进行简单协变量调整
Simple Covariate Adjustment for Many Estimands Using Stable Balancing Weights
arXiv 2609.01638 · 2026-09-03基于几何原生的DSMC矩场支持监测机器学习重建
Geometry-native machine learning reconstruction of DSMC moment fields with support monitoring
arXiv 2609.01637 · 2026-09-03GRAND-HC：图优化作者名消歧
GRAND-HC: Graph-Refined Author Name Disambiguation
arXiv 2609.01636 · 2026-09-03几何社区检测中的无离散化精确恢复
Discretization-free exact recovery in geometric community detection
arXiv 2609.01635 · 2026-09-03二阶弦-卡罗尔流体动力学中的曲率驱动自旋输运
Curvature-driven spin transport in rank-two string-Carroll hydrodynamics
arXiv 2609.01634 · 2026-09-03f(R,T)引力中的跑动真空宇宙学：观测约束与热力学分析
Running Vacuum Cosmology in f(R,T) Gravity: Observational Constraints and Thermodynamic Analysis
arXiv 2609.01632 · 2026-09-03图神经网络团队推荐：一种集成方法
Graph Neural Team Recommendation: An Integrated Approach
arXiv 2609.01631 · 2026-09-03f(R,ϕ,X)引力下的带电各向异性致密星：采用赖斯纳-诺德斯特龙外解的I类嵌入方法
Charged Anisotropic Compact Stars in $f(R,ϕ,X)$ Gravity: A Class I Embedding Approach with Reissner-Nordström Exterior
arXiv 2609.01630 · 2026-09-03幂律 $f(Q,L_m)$ 引力中具有里奇截断的Barrow全息暗能量：晚期宇宙动力学
Barrow Holographic Dark Energy with a Ricci Cutoff in Power-Law $f(Q,L_m)$ Gravity: Late-Time Cosmological Dynamics
arXiv 2609.01629 · 2026-09-03电子商务赞助搜索中联合排名拍卖与固定价格列表的边际预期收益
Marginal Expected Revenue for Jointly Ranking Auction and Fixed-Price Listings in E-Commerce Sponsored Search
arXiv 2609.01628 · 2026-09-03大语言模型在推荐系统解释评估中的实用性
The Utility of LLMs in Recommender Systems Explanation Evaluation
arXiv 2609.01627 · 2026-09-03能量守恒、洛伦兹不变性与第二时间维度
Energy Conservation, Lorentz Invariance and a Second Dimension of Time
arXiv 2609.01626 · 2026-09-03谁的判断算数？众包内容审核中的代表性差距导致对感知毒性的保护不平等
Whose Judgments Count? Representation Gaps in Crowdsourced Content Moderation Produce Unequal Protection from Perceived Toxicity
arXiv 2609.01625 · 2026-09-03RecEvolve：一种用于推荐系统的知识驱动型自主智能体系统
RecEvolve: A Knowledge-Driven Autonomous Agent System for Recommender Systems
arXiv 2609.01622 · 2026-09-03文献数据在材料发现中误导人工智能的情况
When Literature Data Mislead Artificial Intelligence in Materials Discovery
arXiv 2609.01621 · 2026-09-03MGDiff：基于掩码GNN引导扩散模型的多兴趣序列推荐
MGDiff: Multi-Interest Sequence Recommendation with Masking GNN-Guided Diffusion
arXiv 2609.01619 · 2026-09-03面向电信SNOC环境中高效云知识库搜索的多智能体检索增强生成
Multi-Agent Retrieval-Augmented Generation for Efficient Cloud Knowledge Base Search in Telecom SNOC Environment
arXiv 2609.01618 · 2026-09-03结合知识图谱扩展、RRF融合及分块 grounded 评估的混合检索增强生成技术用于企业文档搜索
Hybrid Retrieval-Augmented Generation with Knowledge Graph Expansion, RRF Fusion, and Per-Chunk Grounded Evaluation for Enterprise Document Search
arXiv 2609.01617 · 2026-09-03事件记忆：无需训练的运行时记忆，通过序列模式挖掘与分层速度检索实现
Incident Memory: Training-Free Operational Memory through Sequential Pattern Mining and Velocity-Stratified Retrieval
arXiv 2609.01616 · 2026-09-03提示空间元学习无法跨用户迁移：基于冻结大语言模型的负面结果
Prompt-Space Meta-Learning Does Not Transfer Across Users: A Frozen-LLM Negative Result
arXiv 2609.01615 · 2026-09-03RunSoC 2.0：异构MPSoC中面向硬件分区的汽车软件任务调度与分配
RunSoC 2.0: Scheduling and Allocating Automotive Software Tasks to Hardware Partitions in Heterogeneous MPSoCs
arXiv 2609.01614 · 2026-09-03快速浏览与跳过：用于高效多模态检索的分层自适应推理
Skim and Skip: Hierarchical Adaptive Inference for Efficient Multimodal Retrieval
arXiv 2609.01613 · 2026-09-03MESSY STREETS：面向真实世界地址地理编码的基准测试集
MESSY STREETS: A Benchmark for Geocoding Real-World Addresses
arXiv 2609.01612 · 2026-09-03EvalDetectBench：用于衡量前沿语言模型评估感知能力的基准
EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models
arXiv 2609.01611 · 2026-09-03让修订可理解：编辑意图、方法与应用综述
Making Revisions Understandable: A Survey of Edit Intentions, Methods, and Applications
arXiv 2609.01610 · 2026-09-03
