2026-08论文中文摘要
Vibe编程：实践、性能、生产力与风险——一项最新进展综述
Vibe Coding: Practice, Performance, Productivity, and Risk -A State-of-the-Art Review
arXiv 2608.20446 · 2026-08-24一种广义的无限词幺半群：渐近前后缀商与代数结构
A generalized monoid of infinite words: asymptotic prefix-suffix quotients and algebraic structure
arXiv 2608.20444 · 2026-08-24存储于优化器状态，由后续训练赋予价值：阈下特质迁移的因果解释
Stored in Optimizer State, Valued by Later Training: A Causal Account of Subliminal Trait Transfer
arXiv 2608.20442 · 2026-08-24共享物理响应在神经算子库中恢复隐藏排名
Shared Physics Responses Recover Hidden Rankings in Neural Operator Libraries
arXiv 2608.20441 · 2026-08-24神经PDE算子中的错误物理后门
Wrong-Physics Backdoors in Neural PDE Operators
arXiv 2608.20439 · 2026-08-24同行投票的大语言模型智能体压力测试：发现feed诱导的词汇趋同，但分布式来源无可靠的匹配暴露优势
Peer-Voted LLM-Agent Stress Tests Find Feed-Induced Lexical Convergence but No Reliable Matched-Exposure Advantage for Distributed Sources
arXiv 2608.20438 · 2026-08-24图中高效k受限广播支配的注记
A note on efficient k-limited broadcast domination in graphs
arXiv 2608.20437 · 2026-08-24一种多仪器广义 Lomb-Scargle 周期图实现
A Multi-instrument Generalized Lomb-Scargle Periodogram Implementation
arXiv 2608.20436 · 2026-08-24对《可扩展量子机器学习：可训练性、表达能力与效率》的评论：三重态块读出的多项式计算
Comment on "Scalable Quantum Machine Learning: Trainability, Expressivity and Efficiency": Polynomial Evaluation of the Triplet-Block Readout
arXiv 2608.20435 · 2026-08-24用于端到端计算材料发现的大语言模型智能体
An LLM agent for end-to-end computational materials discovery
arXiv 2608.20434 · 2026-08-24类人音乐机器人作为音乐诱发情绪研究的实验接口
Humanoid Musical Robots as Experimental Interfaces for Music-Evoked Emotion
arXiv 2608.20433 · 2026-08-24ProofJudge：基于工具的大语言模型（LLM）对Mathlib中形式化证明质量的评估工具
ProofJudge: Tool-Grounded LLM Evaluation of Formal Proof Quality in Mathlib
arXiv 2608.20432 · 2026-08-24关于最小原根的注记
A note on least primitive roots
arXiv 2608.20431 · 2026-08-24RISE：面向世界动作模型的自适应想象
RISE: Adaptive Imagination for World Action Models
arXiv 2608.20430 · 2026-08-24能量加权球谐矩的最大熵编码
Maximum Entropy Encoding of Energy-Weighted Spherical Moments
arXiv 2608.20429 · 2026-08-24变换器中的近似同态与收敛表示
Approximate Homomorphisms and Convergent Representations in Transducers
arXiv 2608.20428 · 2026-08-24BF1：一种用于高效长上下文Transformer的因果二元稀疏注意力改造方案
BF1: A Causal Dyadic Sparse-Attention Retrofit for Efficient Long-Context Transformers
arXiv 2608.20427 · 2026-08-24物理网络中局部学习规则的存储容量
Conservation capacity of local learning rules in physical networks
arXiv 2608.20426 · 2026-08-24一阶结构上的抽象计算：附加内容：从程序到决策树 I
Abstract computation over first-order structures. Extras: From programs to decision trees I
arXiv 2608.20424 · 2026-08-24从热偏好预测到自适应热干预：一种使用生理与环境感知的强化学习方法
From Thermal Preference Prediction to Adaptive Thermal Intervention: A Reinforcement Learning Approach Using Physiological and Environmental Sensing
arXiv 2608.20423 · 2026-08-24重新审视基于细观力学的孔隙弹塑性介质相场模型的流固耦合力学公式
Revisiting the hydromechanical formulation of a micromechanics-based phase-field model for poro-elastoplastic media
arXiv 2608.20422 · 2026-08-24大型语言模型的六大误解：一个极简模型与诊断分类法
Six misconceptions about large language models: A minimal model and diagnostic taxonomy
arXiv 2608.20421 · 2026-08-24范畴论的AI现象学：一种第一人称进路
Categorical AI phenomenology: A first-person approach
arXiv 2608.20420 · 2026-08-24一维极性自旋子液滴
One-dimensional Polar Spinor Droplets
arXiv 2608.20419 · 2026-08-24用于疟疾药物发现的大型语言模型的严格评估：性能、规模与资源效用之间的权衡
Rigorous Evaluation of Large Language Models for Malaria Drug Discovery: Trade-offs in Performance, Scale, and Resource Utility
arXiv 2608.20418 · 2026-08-24多孔介质中不混溶粘性指进的起始与演化建模
Modelling the onset and evolution of immiscible viscous fingering in porous media
arXiv 2608.20417 · 2026-08-24SARS-CoV-2的弗林蛋白酶切割位点在人类中的出现时间被限定在2019年末：对COVID-19起源的启示
Emergence of the SARS-CoV-2 furin cleavage site in humans is constrained to late 2019: implications for COVID-19 origins
arXiv 2608.20416 · 2026-08-24涌现暗能量模型的比较研究
A comparative study of emergent dark energy models
arXiv 2608.20415 · 2026-08-24StateSight：评测视觉语言模型中的潜在空间状态重建能力
StateSight: Benchmarking Latent Spatial-State Reconstruction in Vision-Language Models
arXiv 2608.20414 · 2026-08-24BioFirewall：面向智能体AI设计阶段生物安全筛查的基因组写入原生治理层
BioFirewall: A genome-writing-native governance layer for design-stage biosecurity screening of agentic AI
arXiv 2608.20413 · 2026-08-24PEN-STACK：用于基因组写作的语言模型智能体的非制造工具层
PEN-STACK: A non-fabricating tool layer for language-model agents in genome writing
arXiv 2608.20412 · 2026-08-24作为可精确求解模型的图on自旋系统
Graphon Spin Systems as Exactly Solvable Models
arXiv 2608.20410 · 2026-08-24类似蜈蚣的 metastrip 实现按需可编程液滴运动
Centipede-Like Metastrip Enables On-Demand Programmable Droplet Motion
arXiv 2608.20409 · 2026-08-24Columnar-Embedder：一种受生物启发的皮层架构，用于二进制稀疏分布式图表示
Columnar-Embedder: A Biologically Inspired Cortical Architecture for Binary Sparse Distributed Graph Representations
arXiv 2608.20408 · 2026-08-24三元$\Gamma$-半模中的Barr正合性与基于同余的同调代数
Barr-Exactness and Congruence-Based Homological Algebra in Ternary $Γ$-Semimodules
arXiv 2608.20407 · 2026-08-24神经网络函数空间中基于威尔逊定点与有限宽度修正的临界性
Criticality in Neural Network Function Space through Wilsonian Fixed Points and Finite-Width Corrections
arXiv 2608.20403 · 2026-08-24灵枢（LingShu）：连接中医与现代生物医学的大规模以症状为中心的上下文知识图谱
LingShu: A Large-Scale Symptom-Centric Contextualized Knowledge Graph Bridging Traditional Chinese Medicine and Modern Biomedicine
arXiv 2608.20402 · 2026-08-24环境、智能体及智能体-环境联合系统的世界模型
World models of environment, agent and joint agent-environment systems
arXiv 2608.20401 · 2026-08-24当检索尚未开始时检索就已失败：智能体记忆中作为保留失败的结构间接先决条件驱逐
When Retrieval Fails Before It Begins: Structurally Indirect Prerequisite Eviction as a Retention Failure in Agentic Memory
arXiv 2608.20400 · 2026-08-24傅里叶下确界半格中的形态表示理论：频域深度学习算子的通用分解
Morphological Representation Theory in the Fourier Inf-Semilattice: Universal Decomposition of Frequency-Domain Deep Learning Operators
arXiv 2608.20399 · 2026-08-24环境慢AI：生成式系统的设计原则
Environmental Slow AI: Design Principles for Generative Systems
arXiv 2608.20398 · 2026-08-24Nexus：面向统一内存上智能体大语言模型的深度自适应KV缓存拼接与检索解耦工具路由
Nexus: Depth-Adaptive KV-Cache Splicing and Retrieval-Decoupled Tool Routing for Agentic LLMs on Unified Memory
arXiv 2608.20397 · 2026-08-24自监督语音表征追踪聋/弱听婴幼儿向成人模型的口语语言收敛过程
Self-Supervised Speech Representations Track Spoken Language Convergence to Adult Models in Infants and Children Who Are Deaf/Hard-of-Hearing
arXiv 2608.20396 · 2026-08-24语音到SFT流水线的因子消融：对数据质量与下游迁移的差异化影响
A Factorial Ablation of a Speech-to-SFT Pipeline: Differential Effects on Data Quality and Downstream Transfer
arXiv 2608.20394 · 2026-08-24面向智能体对话AI的风格可控且事实保留生成的知识图谱门控去事实化方法
Knowledge-Graph-Gated Defactualization for Style-Controllable and Fact-Preserving Generation in Agentic Conversational AI
arXiv 2608.20393 · 2026-08-24评估即搜索：会议助手接地故障的自适应发现
Evaluation-as-Search: Adaptive Discovery of Grounding Failures in Meeting Assistants
arXiv 2608.20392 · 2026-08-24ImmigrationReason：面向法律推理研究的美国移民上诉结构化数据集
ImmigrationReason: A Structured Dataset of U.S. Immigration Appeals for Legal Reasoning Research
arXiv 2608.20391 · 2026-08-24Ansari：基于检索的伊斯兰AI助手——架构、部署及14万次对话的经验教训
Ansari: A Retrieval-Grounded Islamic AI Assistant -- Architecture, Deployment, and Lessons from 140,000 Conversations
arXiv 2608.20390 · 2026-08-24表征影响检索：多模态智能体框架中技能发现与路由的案例研究
Representation Affects Retrieval: A Case Study of Skill Discovery and Routing in a Multimodal Agent Harness
arXiv 2608.20389 · 2026-08-24意图引擎：面向计算连续体中意图驱动编排的自然语言意图翻译
Intent Engine: Natural-Language Intent Translation for Intent-Driven Orchestration in the Compute Continuum
arXiv 2608.20388 · 2026-08-24
