2026-08论文中文摘要
关于无选择链条件的评论
Comments on Choiceless Chain Conditions
arXiv 2608.26230 · 2026-08-28绿色软件格局：关于演进、应用、软件生命周期及最佳实践的系统映射研究
The Green Software Landscape: A Systematic Mapping Study on Evolution, Applications, Software Lifecycle, and Best Practices
arXiv 2608.26229 · 2026-08-28PathoMIC：用于跨物种抗菌肽活性预测的基准测试
PathoMIC: A Benchmark for Cross-Species Antimicrobial Peptide Activity Prediction
arXiv 2608.26228 · 2026-08-28Alfred：一个灵活、易用的系外行星确认Python软件包
Alfred: A Flexible, User-Friendly Python Package for Exoplanet Confirmation
arXiv 2608.26227 · 2026-08-28面向时间序列的大语言模型（LLM）智能体：一项综述
LLM Agents for Time-Series: A Survey
arXiv 2608.26226 · 2026-08-28智能体网格：非幂等智能体委托的可靠性原语——身份充分性与证据充分性
Agent Mesh: Reliability Primitives for Non-Idempotent Agent Delegation - Identity Adequacy and Evidence Adequacy
arXiv 2608.26225 · 2026-08-28用于CMS开放数据类触发事件选择的经典与混合量子机器学习：基于8量子比特、PCA约束的基准测试
Classical and Hybrid Quantum Machine Learning for Trigger-Like Event Selection on CMS Open Data: An Eight-Qubit, PCA-Constrained Benchmark
arXiv 2608.26224 · 2026-08-28超越边割：面向片上网络（NoC）网格架构的脉冲神经网络（SNN）的活动加权多播超图映射
Beyond Edge Cuts: Activity-Weighted Multicast Hypergraph Mapping for Spiking Neural Networks on Mesh NoCs
arXiv 2608.26223 · 2026-08-28NeuronFuzz：面向大语言模型安全评估的安全神经元引导模糊测试
NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation
arXiv 2608.26222 · 2026-08-28生成式智能体的提示敏感性：来自流行病模型的证据
Prompt Sensitivity of Generative Agents: Evidence from an Epidemic Model
arXiv 2608.26221 · 2026-08-28MeshReduce-U：面向Mesh NoC上不规则神经归约的编译器引导式通信缩减方案
MeshReduce-U: Compiler-Guided Communication Reduction for Irregular Neural Reductions on Mesh NoCs
arXiv 2608.26220 · 2026-08-28TRACE：稀疏结构化感知下物理场的回溯式流生成
TRACE: Retrospective Streaming Generation of Physical Fields under Sparse Structured Sensing
arXiv 2608.26219 · 2026-08-28相同模型，不同工具链：编码智能体的结果差异
Same Model, Different Harness: Different Coding-Agent Results
arXiv 2608.26218 · 2026-08-28获取JWST（詹姆斯·韦伯空间望远镜）NIRCam（近红外相机）数据天体测量观测的最佳实践
Best practices for obtaining astrometric observations from JWST (274) NIRCam data
arXiv 2608.26217 · 2026-08-28基于神经网络模拟器的等离子体形状控制实时虚拟电路：在MAST-U PCS中的集成与测试
Real-time virtual circuits for plasma shape control via neural network emulators: integration and testing in the MAST-U PCS
arXiv 2608.26216 · 2026-08-28基于AI的软件质量研究：挑战与贡献——一项系统映射研究
Challenges and Contributions in Quality of AI-Based Software: A Systematic Mapping Study
arXiv 2608.26215 · 2026-08-28手术视频生成：从扩散模型到世界模型：综述
Surgical Video Generation From Diffusion to World Models: A Survey
arXiv 2608.26214 · 2026-08-28用于鲁棒视听语音识别中对比解码的注意力引导可靠性缩放
Attention-Guided Reliability Scaling for Contrastive Decoding in Robust Audio-Visual Speech Recognition
arXiv 2608.26213 · 2026-08-28带协变量的治愈模型中基于Copula的相依删失
Copula based dependent censoring in cure models with covariates
arXiv 2608.26212 · 2026-08-28开源卫星软件的全景特征分析
Characterizing the Landscape of Open-Source Satellite Software
arXiv 2608.26211 · 2026-08-28多模态风险轨迹揭示痴呆的异质性路径
Multimodal risk trajectories reveal heterogeneous paths to dementia
arXiv 2608.26210 · 2026-08-28公平性不变量：一种解释和缓解公平性缺陷的关系方法
Fairness Invariants: A Relational Approach to Explaining and Mitigating Fairness Bugs
arXiv 2608.26209 · 2026-08-28核科学与技术的前沿问题及新兴方向
Frontier Questions and Emerging Directions in Nuclear Science and Technology
arXiv 2608.26207 · 2026-08-28Ankhdjet：基于开放PDK的掩码编程三元存算一体的开源编译器
Ankhdjet: An Open-Source Compiler for Mask-Programmed Ternary Compute-in-ROM on an Open PDK
arXiv 2608.26206 · 2026-08-28超越参与者水平交叉验证：纵向机器学习的可靠推断
Beyond Participant-Level Cross-Validation: Reliable Inference for Longitudinal Machine Learning
arXiv 2608.26205 · 2026-08-28宇宙黑洞的粗略估计最大质量
Crudely Estimated Maximum Mass for a Cosmological Black Hole
arXiv 2608.26203 · 2026-08-28用于BICEP阵列BA4-90/150接收机的钛过渡边缘传感器晶圆工程
Engineering of titanium transition edge sensor wafers for the BA4-90/150 receiver of BICEP Array
arXiv 2608.26202 · 2026-08-28程氏多元拧数多项式的刻画
The Characterization of Cheng's Multivariate Writhe Polynomial
arXiv 2608.26201 · 2026-08-28通过MCP工具调用对硬件设计自动化的AI智能体进行基准测试
Benchmarking AI Agents for Hardware Design Automation via MCP Tool Calling
arXiv 2608.26199 · 2026-08-28用于纳米尺度表征科学仪器操作的智能体AI
Agentic AI for operating scientific instruments for nanoscale characterization
arXiv 2608.26198 · 2026-08-28利用工程实现可预测的智能体系统：确定性执行约束的实证研究
Harness Engineering for Predictable Agentic Systems: An Empirical Study of Deterministic Execution Constraints
arXiv 2608.26197 · 2026-08-28基于最优$H^2$-嵌入的平移圆盘玻尔型不等式
Bohr-Type Inequalities for Shifted Disks via Optimal $H^2$-Embeddings
arXiv 2608.26196 · 2026-08-28大语言模型智能体轨迹中的成本-效用对齐：分析、归因、诊断、适配与评估
Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluation
arXiv 2608.26195 · 2026-08-28用于协调异构语音和文本检索器的重排序器
A Reranker for Orchestrating Heterogeneous Speech and Text Retrievers
arXiv 2608.26194 · 2026-08-28AffectOmni：面向社交与艺术相关场景的可通过强化学习验证的以人为中心的接地情感推理
AffectOmni: RL-Verifiable People-Centric Grounded Affective Reasoning for Social and Art-Related Scenes
arXiv 2608.26193 · 2026-08-28面向多模态纵向电子健康记录（EHR）的事件风险预测的结构化证据路由
Structured Evidence Routing for Incident Risk Prediction from Multimodal Longitudinal EHRs
arXiv 2608.26191 · 2026-08-28用潜世界模型预测后果并强化导航策略
Predicting Consequences and Reinforcing Navigation Policies with Latent World Models
arXiv 2608.26190 · 2026-08-28使用工具的智能体在调用层面的可靠性
Invocation-Level Reliability of Tool-Using Agents
arXiv 2608.26189 · 2026-08-28你的社区安全吗？大型语言模型城市安全判断中的基于地点的污名
Is Your Neighborhood Safe? Place-based Stigma in Large Language Models' Urban Safety Judgments
arXiv 2608.26188 · 2026-08-28探究提示词与响应语言对大语言模型内容生成的影响
Investigating the Influence of Prompt and Response Languages on LLM Content Generation
arXiv 2608.26186 · 2026-08-28你能帮我说出这句话吗？：在同地讨论中通过代理发声
Can You Say This for Me? Speaking Up by Proxy in Co-Located Discussion
arXiv 2608.26185 · 2026-08-28TutorTrace：用于AI辅助编程教育中学习者行为状态分类的数据集与分类体系
TutorTrace: A Dataset and Taxonomy for Classifying Learner Behavioral States during AI-Assisted Programming Education
arXiv 2608.26184 · 2026-08-28打造我自己的验证器调用清洁的证据包的四种方法：证据包验证器的拒绝点变异测试
Four Ways to Forge a Bundle My Own Verifier Calls Clean: Refusal-Site Mutation Testing of an Evidence-Bundle Verifier
arXiv 2608.26183 · 2026-08-28我的机器人为什么刚改变了人格？面向基于大语言模型（LLM）的人机交互（HRI）的具身机器人人格提示设计指南
Why did My Robot Just Change Personality? Prompting Guidelines for a Grounded Robot Persona in LLM-Based HRI
arXiv 2608.26182 · 2026-08-28关于$\boldsymbol{\textit{P}\boldsymbol{\bigtriangleup}(0;1_n)}$上欧拉算子与面积泛函的尖锐型玻尔不等式
Sharp Bohr-Type Inequalities Involving Euler Operator and Area Functionals on $\mathbb{P}Δ(0;1_n)$
arXiv 2608.26181 · 2026-08-28PACEShop：评估个性化、可操作、可组合且基于证据的购物助手
PACEShop: Evaluating Personalized, Actionable, Compositional, and Evidence-grounded Shopping Assistants
arXiv 2608.26180 · 2026-08-28通过幂零系统的局部刚性研究幂零系统的因子闭包
Factor-Closure of Pro-Nilsystems via Local Rigidity of Nilsystems
arXiv 2608.26179 · 2026-08-28基于大语言模型的长文本生成中大纲阶段的多框架对比
A Multi-Framework Comparison of Outline Stages in Long-Form Generation with LLMs
arXiv 2608.26177 · 2026-08-28知识卡片：面向AI系统的结构化知识
Knowledge Cards: Structured Knowledge for AI Systems
arXiv 2608.26176 · 2026-08-28压缩中的迷失：抽取式提示压缩器的受控跨语言审计
Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressors
arXiv 2608.26175 · 2026-08-28
