2026-08论文中文摘要
大型语言模型在化妆品化学与皮肤健康领域的准确性与可靠性：一项基准测试研究
Accuracy and Reliability of Large Language Models in Cosmetic Chemistry and Skin Health: A Benchmarking Study
arXiv 2608.14631 · 2026-08-18表征语言模型决策中的修辞失配问题
Characterizing Rhetorical Misalignment in Decision-Making with Language Models
arXiv 2608.14630 · 2026-08-18大语言模型推理时的对抗性政治偏见缓解
Inference-Time Mitigation of Adversarial Political Bias in Large Language Models
arXiv 2608.14629 · 2026-08-18基于超图、多拟阵和Tutte多项式的高阶自旋模型形式框架
A formal framework for higher-order spin models via hypergraphs, polymatroids, and the Tutte polynomial
arXiv 2608.14628 · 2026-08-18面向分布式智能的AI原生6G：流量特性、感知与AI网格
AI-Native 6G for Distributed Intelligence: Traffic Characteristics, Awareness, and AI Grid
arXiv 2608.14627 · 2026-08-18低资源语言下的大语言模型安全对齐：系统文献综述
LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review
arXiv 2608.14626 · 2026-08-18健康科学领域中用于人类三重盲同行评审的本地AI预筛选
Local AI pre-screening for human triple-blind peer review in health sciences
arXiv 2608.14625 · 2026-08-18面向智能体服务的KV缓存管理的智能体执行学习
Learning Agent Execution for KV-Cache Management in Agentic Serving
arXiv 2608.14624 · 2026-08-18射影空间与格拉斯曼流形上的理想类映射
Ideal class maps on projective spaces and Grassmannians
arXiv 2608.14623 · 2026-08-18以人为中心的基准测试大型语言模型（LLM）育儿建议方法
A Human-Centred Approach to Benchmarking LLMs for Parenting Advice
arXiv 2608.14622 · 2026-08-18AutoMem：面向自动化记忆架构搜索的文本梯度递归自改进框架
AutoMem: A Text-Gradient Recursive Self-Improvement Framework for Automated Memory Architectures Search
arXiv 2608.14621 · 2026-08-18解释自适应系统中强化学习的决策
Explaining Reinforcement Learning Decisions in Self-adaptive Systems
arXiv 2608.14620 · 2026-08-18PIKFNO：一种基于物理信息核函数的可解释神经算子
PIKFNO: An Interpretable Neural Operator Based on Physics Informed Kernel Function
arXiv 2608.14619 · 2026-08-18有限交换环中的理想零乘积概率
Ideal Zero-Product Probability in Finite Commutative Rings
arXiv 2608.14618 · 2026-08-18校准的信任，而非更精确的预测：不确定性融合的实证检验
Calibrated Trust, Not Sharper Prediction: An Empirical Test of Uncertainty Fusion
arXiv 2608.14617 · 2026-08-18滥用的痕迹：生成式AI如何影响基于图像的性虐待（IBSA）调查
Traces of Abuse: How Generative AI Impacts Image-Based Sexual Abuse (IBSA) Investigations
arXiv 2608.14616 · 2026-08-18大语言模型及其对力学与空间几何的认知能力
Large Language Models and their Awareness of Mechanics and Spatial Geometry
arXiv 2608.14615 · 2026-08-18DumpsterCluster：从“废品回收”到在60美元级GPU上部署LLaMA-70B
DumpsterCluster: From Dumpster Diving to Serving LLaMA-70B on $60 GPUs
arXiv 2608.14614 · 2026-08-18大语言模型智能体是否进行理性协商？面向A2A/MCP的可验证多智能体交互机制设计框架
Do LLM Agents Negotiate Rationally? A Mechanism-Design Framework for Verifiable Multi-Agent Interaction over A2A/MCP
arXiv 2608.14613 · 2026-08-18基于偏差泛函的Banach型不动点定理
A Banach-Type Fixed Point Theorem via Discrepancy Functionals
arXiv 2608.14612 · 2026-08-182026年新加坡全球AI安全研究优先事项共识
The 2026 Singapore Consensus on Global AI Safety Research Priorities
arXiv 2608.14611 · 2026-08-18大型语言模型何时适用错误法律？诊断大型语言模型在时间法律推理中的失败
When Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning
arXiv 2608.14610 · 2026-08-18工作场所中AI焦虑的理解：基于恐惧习得理论与技术接受模型的多方法研究
Understanding AI Anxiety in the Workplace: A Multimethod Investigation Using Fear Acquisition Theory and the Technology Acceptance Model
arXiv 2608.14609 · 2026-08-18采样的玻尔兹曼结构：固有p值及其涌现的闭式表达式
The Boltzmann structure of sampling: Intrinsic $p$-value and its emergent closed-form expression
arXiv 2608.14608 · 2026-08-18看似合理但并非有效：对大型语言模型（LLMs）作为合成调查受访者的心理计量学审查
Plausible but Not Valid: A Psychometric Audit of LLMs as Synthetic Survey Respondents
arXiv 2608.14606 · 2026-08-18高等教育中生成式AI使用的学术诚信的心理决定因素
Psychological Determinants of Academic Integrity in the Use of Generative AI in Higher Education
arXiv 2608.14605 · 2026-08-18Wiola 13M：一种用于参数高效小型语言模型的门控螺旋注意力架构
Wiola 13M, a Gated Spiral Attention Architecture for Parameter Efficient Small Language Models
arXiv 2608.14604 · 2026-08-18推荐的自我：真实性与算法过滤
Recommended Selves: Authenticity and Algorithmic Filtering
arXiv 2608.14602 · 2026-08-18OneBarrier：网络必须为透明容错提供什么以实现无开销的容错
OneBarrier: What a Network Must Provide for Transparent Fault Tolerance to Be Free
arXiv 2608.14601 · 2026-08-18演示：基于设备端意图感知语义分解的实时生成多播
Demo: Real-time Generative Multicasting with On-Device Intent-aware Semantic Decomposition
arXiv 2608.14600 · 2026-08-18立场：医学人工智能忽视真实治疗结局
Position: Medical AI Neglects Real Treatment Outcomes
arXiv 2608.14598 · 2026-08-18基于DDS通信的异构系统实时患者监护
Real-Time Patient Monitoring with Heterogeneous Systems Using DDS-Based Communication
arXiv 2608.14597 · 2026-08-18MacDowell-Mansouri σ模型
MacDowell-Mansouri $σ$-model
arXiv 2608.14596 · 2026-08-18网络空间搜索意图作为主动交通热点检测的先行指标
Cyberspace Search Intentions as Leading Indicators for Proactive Traffic Hotspot Detection
arXiv 2608.14595 · 2026-08-18几何并非鲁棒性：PGD评估的轨迹级研究
Geometry Is Not Robustness: A Trajectory-Level Study of PGD Evaluation
arXiv 2608.14594 · 2026-08-18BC-DIR：面向V2X网络中QUIC的带Bandit控制的感知截止时间的增量冗余
BC-DIR: Bandit-Controlled Deadline-Aware Incremental Redundancy for QUIC in V2X Networks
arXiv 2608.14593 · 2026-08-18面向隐私受限车载网络的低延迟空间溯源恢复方法
Low-Latency Spatial-Provenance Recovery Methods for Privacy-Constrained Vehicular Networks
arXiv 2608.14592 · 2026-08-186G原生AI与信道基础模型
6G Native AI and Channel Foundation Models
arXiv 2608.14591 · 2026-08-18面向安全的大语言模型智能体：规范、验证与执行的综述
Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement
arXiv 2608.14590 · 2026-08-18云原生5G核心网中UPF数据平面I/O模式的比较：SD-Core BESS-UPF上的AF_PACKET、AF_XDP、CNDP和DPDK
Comparing UPF Dataplane I/O Modes in a Cloud-Native 5G Core: AF_PACKET, AF_XDP, CNDP, and DPDK on SD-Core BESS-UPF
arXiv 2608.14589 · 2026-08-18幻觉滚雪球：将多智能体大语言模型流水线中的错误传播建模为状态转移
The Hallucination Snowball: Modeling Error Propagation as State Transitions in Multi-Agent LLM Pipelines
arXiv 2608.14588 · 2026-08-18一种结合规则与大语言模型（LLM）的智能体框架，用于描述性文档布局的嵌入与标注：植物科学应用案例
An Agentic Framework Using Rules and LLMs for Embedding and Annotating Descriptive Document Layouts: A Plant Science Use Case
arXiv 2608.14587 · 2026-08-18面向混合架构的视觉-语言-动作（VLA）高效块级并行推理
Efficient Block-Layer Parallel Inference for Vision-Language-Action on Hybrid Architectures
arXiv 2608.14586 · 2026-08-18Euclid-Omni：面向平面几何的统一神经符号框架
Euclid-Omni : A Unified Neuro-Symbolic Framework for Plane Geometry
arXiv 2608.14585 · 2026-08-18多模态生成模糊系统：模糊推理引导的大模型交互式问答框架
Multi-Modal Generative Fuzzy System: Fuzzy Inference Guided Large Model Interactive Question Answering Framework
arXiv 2608.14584 · 2026-08-18利用Veins仿真评估对抗性交通模式对VANET通信的影响
Evaluating the impact of adversarial traffic patterns on vanet communication using veins simulation
arXiv 2608.14583 · 2026-08-18利用ACE Omni平台开展电信中继服务研究
Enabling Telecommunication Relay Service Research with ACE Omni Platform
arXiv 2608.14582 · 2026-08-18基于动态模态分解从含噪低分辨率测量中表征热系统
Characterization of Thermal Systems from Noisy and Low-resolution Measurements Using Dynamic Mode Decomposition
arXiv 2608.14581 · 2026-08-18OGX：开源、厂商中立的生成式AI应用服务器
OGX: An Open-Source, Vendor-Neutral Generative AI Application Server
arXiv 2608.14580 · 2026-08-18SKILL：用于逻辑优化的自校正知识引导迭代大语言模型智能体
SKILL: Self-correcting Knowledge-guided Iterative Large Language Model Agent for Logic Optimization
arXiv 2608.14579 · 2026-08-18
