2026-09论文中文摘要
图卢法律理解中的跨语言迁移：依赖文字脚本的性能提升与检索增强生成（RAG）引发的知识冲突
Cross Lingual Transfer in Tulu Legal Comprehension: Script-Dependent Improvement and RAG-Induced Knowledge Conflict
arXiv 2608.28645 · 2026-09-01测量语言模型智能体群体中的集体语义变化
Measuring Collective Semantic Change in Populations of Language Model Agents
arXiv 2608.28644 · 2026-09-01深度研究写作的重新设计与审计以生成忠实报告
Redesigning and Auditing Deep Research Writing for Faithful Reports
arXiv 2608.28643 · 2026-09-01从抽取到受管控的记忆：结合领域专家评审的多智能体知识图谱构建
From Extraction to Governed Memory: Multi-Agent Knowledge Graph Construction with Domain-Expert Review
arXiv 2608.28642 · 2026-09-01Terminal-Bench-LILT：基于语言、区域与文化的多语言智能体编码基准
Terminal-Bench-LILT: Multilingual Agentic Coding Benchmark Grounded in Language, Region, and Culture
arXiv 2608.28641 · 2026-09-01PromptKWS：一种新型的提示引导式开放词汇关键词 spotting 框架
PromptKWS: A Novel Prompt-Guided Open-Vocabulary Keyword Spotting Framework
arXiv 2608.28640 · 2026-09-01用于形式化定理证明的奖励-预言机蒙特卡洛树搜索：样本高效搜索与内核级证明审计的必要性
Reward-Oracle MCTS for Formal Theorem Proving: Sample-Efficient Search and the Need for Kernel-Level Proof Auditing
arXiv 2608.28639 · 2026-09-01基于代理引导的求解与复现的自进化技能
Self-Evolving Skills via Surrogate-Guided Solve-and-Reproduce
arXiv 2608.28638 · 2026-09-01AI科学家任务控制（AIMC）：面向自主科学发现的人类监督的可视分析
AI Scientist Mission Control (AIMC): Visual Analytics for Human Oversight of Autonomous Scientific Discovery
arXiv 2608.28637 · 2026-09-01三维clothoid的显式笛卡尔坐标
Explicit Cartesian Coordinates for Three-Dimensional Clothoids
arXiv 2608.28636 · 2026-09-01多模态大语言模型（MLLMs）真的理解低资源高棉语文档吗？一项关于高棉语文档视觉问答（VQA）的试点研究
Do MLLMs Really Understand Low-Resource Khmer Documents? A Pilot Study on Khmer Document VQA
arXiv 2608.28635 · 2026-09-01用于计算一般图适应度中心性的非线性不动点迭代的收敛性与加速
Convergence and acceleration of a nonlinear fixed-point iteration for computing the Fitness Centrality of general graphs
arXiv 2608.28634 · 2026-09-01PAUSE：用于长篇文化故事改编的可编辑策略制品
PAUSE: Editable Strategy Artifacts for Long-Form Cultural Story Adaptation
arXiv 2608.28633 · 2026-09-01CrossAudit：面向智能体科学的原生Git跨供应商审计循环
CrossAudit: A Git-Native, Cross-Vendor Audit Loop for Agentic Science
arXiv 2608.28631 · 2026-09-01通过广义风格感知全双工框架实现主动口语话轮
Enabling Proactive Spoken Turns via a Generalized Style-Aware Full-Duplex Framework
arXiv 2608.28630 · 2026-09-01基于领域专用大语言模型的BIM设计缺陷智能识别与修复
Intelligent Identification and Repair of Design Defects in BIM via Domain-Specific Large Language Models
arXiv 2608.28629 · 2026-09-01CDEP智能体：将气象检测到的时间复合事件与现实世界的文献证据相连接
CDEP Agent: Connecting Meteorologically Detected Temporal Compound Events to Real-World Documentary Evidence
arXiv 2608.28628 · 2026-09-01机器学习增强的禁忌搜索算法在战术无线网络设计中的应用
Machine Learning-Enhanced Tabu Search for Tactical Wireless Network Design
arXiv 2608.28627 · 2026-09-01大型语言模型是否会仔细审查其评审内容？一项关于评分校准、错误检测及作者身份影响的多模态审计研究
Do large language models scrutinise what they review? A multimodal audit of scoring calibration, error detection, and author-identity effects
arXiv 2608.28626 · 2026-09-01面向科学文献表示的文档内非对称预测学习
Asymmetric Within-Document Predictive Learning for Scientific Document Representation
arXiv 2608.28625 · 2026-09-01MA-RAG：用于帕金森病纵向评估查询驱动式摘要的多智能体检索增强生成框架
MA-RAG: Multi-Agent Retrieval-Augmented Generation for Query-Driven Summarization of Longitudinal Parkinson's Disease Assessments
arXiv 2608.28624 · 2026-09-01PUFFER：面向持续演化语料库的增量模糊去重算法
PUFFER: Incremental Fuzzy Deduplication for Continuously Evolving Corpora
arXiv 2608.28622 · 2026-09-01专家对如何打击AI生成的虚假信息存在分歧，但一致认为健康与政治领域需采用不同解决方案
Experts Disagree on How to Fight AI Disinformation, but Agree That Health and Politics Need Different Solutions
arXiv 2608.28621 · 2026-09-01用于策略优化的偏好 elicitation 及其在心脏移植与人类价值观对齐中的应用
Preference Elicitation for Policy Optimization and Application to Aligning Heart Transplantation with Human Values
arXiv 2608.28620 · 2026-09-01从生成式AI虚拟患者对话日志到教师可解释的过程证据：一项高等教育中的学习分析研究
From GenAI Virtual Patient Dialogue Logs to Teacher-Interpretable Process Evidence: A Learning Analytics Study in Higher Education
arXiv 2608.28619 · 2026-09-01预测竞赛编程中的学生流失：结合调查洞察与全球行为日志的大规模研究
Predicting Student Attrition in Competitive Programming: A Large-Scale Study Integrating Survey Insights and Global Behavioral Logs
arXiv 2608.28618 · 2026-09-01AI辅助探究能否提升学生在社会科学议题中的决策能力？一项关于气候变化的三组实验研究
Can AI-Assisted Inquiry Enhance Students' Decision-Making Skills in Socio-Scientific Issues? A Three-Group Experimental Study on Climate Change
arXiv 2608.28617 · 2026-09-01导师职业阶段与博士生被指导者成果
Advisor career stage and PhD advisee outcomes
arXiv 2608.28616 · 2026-09-01STAGEET：以阿拉伯语为案例的分阶段类型化编辑标记语法纠错方法
STAGEET: Stage-wise Typed Edit Tagging for Grammatical Error Correction with Arabic as a Case Study
arXiv 2608.28614 · 2026-09-01银幕惯性：好莱坞电影中持续存在的种族与性别差异（1900-2024）
On-Screen Inertia: Persistent Racial and Gender Disparities in Hollywood Film (1900-2024)
arXiv 2608.28613 · 2026-09-01InternReviewer与InternAdvocate：面向同行评审与反驳的智能体强化学习的客观奖励与评估
InternReviewer & InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcement Learning in Peer Review and Rebuttal
arXiv 2608.28612 · 2026-09-01Gurukul AI：面向印度教育体系的交互式AI驱动教育平台
Gurukul AI: An Interactive AI-Driven Educational Platform for Indian Education System
arXiv 2608.28611 · 2026-09-01TPvG：基于一次性反馈到序列反馈的大语言模型道德决策框架
TPvG: A Moral Decision Framework for Large Language Models from One-Shot to Sequential Feedback
arXiv 2608.28610 · 2026-09-01参数化多模态用户记忆：存储字幕无法承载的内容
Parametric Multimodal User Memory: Storing What Captions Cannot Carry
arXiv 2608.28609 · 2026-09-01NLP驱动的古印度翻译医学文本知识提取与主题分类
NLP-Driven Knowledge Extraction and Thematic Classification of Translated Ancient Indian Medical Texts
arXiv 2608.28608 · 2026-09-01RegDivergence-101：用于生命科学领域跨司法管辖区监管矛盾检测的大语言模型基准
RegDivergence-101: An LLM Benchmark for Cross-Jurisdiction Regulatory Contradiction Detection in Life Sciences
arXiv 2608.28607 · 2026-09-01认知单元：小型语言模型群体的组合框架
Cognitive Cells: A Compositional Framework for Populations of Small Language Models
arXiv 2608.28606 · 2026-09-01MedTVL：利用视觉与语言进行医学时间序列分类
MedTVL: Harnessing Vision and Language for Medical Time Series Classification
arXiv 2608.28605 · 2026-09-01品牌战争：面向限时英语作为外语写作的游戏化AI反馈系统
The Brand War: A Gamified AI-Feedback System for Time-Limited EFL Writing
arXiv 2608.28604 · 2026-09-01C3-UniMM：通过超级对齐与共享解码空间实现因果循环一致性的统一多模态建模
C3-UniMM: Causal Cycle-Consistent Unified Multimodal Modeling via Super Alignment and Shared Decoding Space
arXiv 2608.28603 · 2026-09-01整合三轴IMU传感器与集成学习用于帕金森病严重程度的有效分类
Integrating Triaxial IMU Sensors and Ensemble Learning for Effective Parkinson Disease Severity Classification
arXiv 2608.28602 · 2026-09-01利用生成式人工智能为本科数学设计可访问的交互式可视化：一个六阶段工作流
Leveraging Generative AI to Design Accessible Interactive Visualizations for Undergraduate Mathematics: A Six-Phase Workflow
arXiv 2608.28601 · 2026-09-01数学推理中思维链的SHAPE
SHAPE of Chain-of-Thought in Math Reasoning
arXiv 2608.28600 · 2026-09-01CDPR：基于反事实优势的成本感知序列医疗诊断信用分配
CDPR: Counterfactual Advantage-based Credit Assignment for Cost-Aware Sequential Medical Diagnosis
arXiv 2608.28599 · 2026-09-01OhmicFlow：基于欧姆定律的极端天气中断下公共交通客流预测方法
OhmicFlow: Forecasting transit passenger flow under extreme weather disruptions via Ohm's law
arXiv 2608.28598 · 2026-09-01在线调查中智能体AI能力与数据质量控制的竞赛
The Race between Agentic AI Capabilities and Data Quality Control in Online Surveys
arXiv 2608.28597 · 2026-09-01Paper Pilot：面向应用科学的可追溯证据的科学手稿生成的人在环专家系统
Paper Pilot: A Human-in-the-Loop Expert System for Evidence-Traceable Scientific Manuscript Generation in Applied Sciences
arXiv 2608.28596 · 2026-09-01噪声中的信号：面向生物医学文本分类的可审计可靠性层
The Signal in the Noise: An Auditable Reliability Layer for Biomedical Text Classification
arXiv 2608.28595 · 2026-09-01从问题优先到分析师优先：面向主动企业分析的领域专家技能与验证知识编译
From Question-First to Analyst-First: Domain-Expert Skills and Verified Knowledge Compilation for Proactive Enterprise Analytics
arXiv 2608.28594 · 2026-09-01法定人工智能：使大语言模型与法律规范对齐
Statutory AI: Aligning Large Language Models With Legal Norms
arXiv 2608.28593 · 2026-09-01
