2026-09论文中文摘要
二元本原三重纠错BCH码的精确第二广义覆盖半径
The Exact Second Generalized Covering Radius of Binary Primitive Triple-Error-Correcting BCH Codes
arXiv 2608.07215 · 2026-09-30超图的边连通性与LLY曲率
Ollivier--Ricci Idleness Functions and Edge-Connectivity of Hypergraphs
arXiv 2608.06029 · 2026-09-30多变量时间序列预测需要跨变量损失
Multivariate Time Series Forecasting needs Cross Variable Loss
arXiv 2608.05742 · 2026-09-30采用卷积编译策略实现最多100比特量子傅里叶变换的实验演示
Experimental demonstration of the Quantum Fourier Transform on up to 100 qubits using a convolutional compilation strategy
arXiv 2608.05435 · 2026-09-30半直积与拟哈密顿群中的隐子群问题
The Hidden Subgroup Problem in Semidirect Products and Quasi-Hamiltonian Groups
arXiv 2608.05321 · 2026-09-30可交换随机变量加权和的更紧Hoeffding界
A Sharper Hoeffding Bound for Weighted Sums of Exchangeable Random Variables
arXiv 2608.04900 · 2026-09-30Active-SWE：针对无问题报告的主动漏洞修复任务的编码智能体基准测试
Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports
arXiv 2608.04682 · 2026-09-30CURATE：利用大语言模型智能体构建、编目和部署可复现工作流
CURATE: Leveraging LLM Agents to Compose, Catalog, and Deploy Reproducible Workflows
arXiv 2608.04270 · 2026-09-30基于FRP的嵌入式系统的多模式调试
Multi-Mode Debugging for FRP-Based Embedded Systems
arXiv 2608.04264 · 2026-09-30Θₙ压缩算子的扩张理论与典范分解
On the Dilation Theory and Canonical Decomposition of $\mathbfΘ_n$-Contractions
arXiv 2608.03574 · 2026-09-30MoEGen：用于实例自适应LoRA生成的混合专家模型
MoEGen: Mixture-of-Experts for Instance-Adaptive LoRA Generation
arXiv 2608.03275 · 2026-09-30语言模型智能体的测试时推理工作量与未授权工具使用：一项预先指定的等效性研究
Low Reasoning Effort Is Enough for Routine Office Work by Language-Model Agents
arXiv 2608.03169 · 2026-09-30离散光锥量子化 $ϕ^4$ 理论中含零模修正的临界耦合
Critical coupling with zero-mode corrections in discretized light-cone quantized $ϕ^4$ theory
arXiv 2608.02972 · 2026-09-30超图上Ollivier-Ricci曲率的空闲度函数
Idleness Functions for Ollivier-Ricci Curvature on Hypergraphs
arXiv 2608.01970 · 2026-09-30A超几何级数的希尔伯特级数与对数次数
Hilbert Series and Logarithmic Degrees of $A$-Hypergeometric Series
arXiv 2608.01778 · 2026-09-30有损非线性传输线中的双曲正切激波
Power-Logistic Shocks in a Lossy Nonlinear Transmission Line
arXiv 2608.00723 · 2026-09-30OpenART：通过开放式环境演化扩展智能体红队演练规模
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution
arXiv 2608.00677 · 2026-09-30基于受损集合观测的鲁棒多项式Freiman-Ruzsa：通过尖锐持续子集BSG编译器实现
Learning Latent Algebraic Structure from Ambiguous Set Observations
arXiv 2608.00451 · 2026-09-30可验证奖励下策略内优化中的验证器诱导支持重塑
Verifier-Induced Support Reshaping in On-Policy Optimization
arXiv 2608.00220 · 2026-09-30面向数据高效RL对齐的宪法网格工具（C-Guard）
C-Instrument: Automating RL Data Generation and Hillclimbing with a Constitution-Grid Instrument
arXiv 2608.00180 · 2026-09-30小语言模型领域适应的可信性代价：一项跨架构实证研究
Trustworthiness Costs of Domain Adaptation in Small Language Models:A Cross-Architecture Empirical Study
arXiv 2608.00042 · 2026-09-30PAC-MAN：用于人形机器人躲避球全身安全性的感知感知CBF-RL框架
PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball
arXiv 2607.28623 · 2026-09-30Beacon：智能体何时及如何执行智能体视觉推理
Beacon: Knowing When and How to Perform Agentic Visual Reasoning
arXiv 2607.28595 · 2026-09-30ORCA-bench：语言模型智能体的值班待命准备程度如何？
ORCA-bench: How Ready Are Language Model Agents for Oncall?
arXiv 2607.28545 · 2026-09-30FaithEyes：通过多智能体过程图像验证实现可信的工具使用
FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Self-Verification
arXiv 2607.28225 · 2026-09-30钨中位错-空位环相互作用下辐照诱导缺陷组态的演化
Evolution of Irradiation-Induced Defect Landscape through Edge Dislocation and Vacancy Loop Interactions in Tungsten
arXiv 2607.27375 · 2026-09-30量子与经典擦除：边界相等但代价不同
Quantum vs Classical Erasure: Equal Bounds but Unequal Costs
arXiv 2607.27341 · 2026-09-30SIGIL：将智能体技能编译为类型化工具框架
SIGIL: Skill Compilation for Reliable and Efficient Agent Execution
arXiv 2607.27309 · 2026-09-30围棋中结合不确定性门控的信念引导决策方法
Belief-Guided Decision Making with Uncertainty Gating in the Game of Go
arXiv 2607.26946 · 2026-09-30WhisperRec：用于高效基础推荐模型的潜在推理方法
OneLatent: Latent Reasoning for Efficient Foundation Recommendation Models
arXiv 2607.26621 · 2026-09-30S2A2：利用声学空间信息进行操作任务的视听模仿学习
S2A2: Audio-Visual Imitation Learning for Manipulation Tasks Using Acoustic Spatial Information
arXiv 2607.26047 · 2026-09-30超引力的耦合流
The coupling flow for supergravity
arXiv 2607.25714 · 2026-09-30使用三混合高性能计算的各向异性自旋系统的有限温度Lanczos方法
Finite-temperature Lanczos for anisotropic spin systems using triple-hybrid high-performance computing
arXiv 2607.25585 · 2026-09-30CodeNib：一种用于向编码代理提供仓库上下文的多视图数据系统
CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents
arXiv 2607.25431 · 2026-09-30用于无线对抗用户检测的贝叶斯引导协作强化学习波束成形
Bayesian-Guided Cooperative RL Beamforming for Wireless Adversarial User Detection
arXiv 2607.25417 · 2026-09-30单臂试验中群体标准化历史对照设计的协变量自适应样本量重新估计
Outcome-blinded sample size re-estimation for externally controlled single-arm trials using baseline covariates
arXiv 2607.25159 · 2026-09-30智能体循环何时会将停滞误认为进步？长期运行的自主语言模型智能体循环中的自我评估偏差与外部基础验证
When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops
arXiv 2607.25152 · 2026-09-30在大型视听检索模型中解锁空间定位
Unlocking Spatial Grounding in Large Audio-Visual Retrieval models
arXiv 2607.24786 · 2026-09-30随机重尾张量的谱方面
Spectral aspects of random heavy-tailed tensors
arXiv 2607.24695 · 2026-09-30LOCKS：用于高效长上下文解码的页面局部紧凑键摘要
LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding
arXiv 2607.24555 · 2026-09-30量子理论物理合理数学模型的基本要素
The bare necessities of a physically reasonable mathematical model for quantum theory
arXiv 2607.24474 · 2026-09-30约束红移z≈1处的中性氢（HI）分布
Constraining the $z \approx 1$ neutral hydrogen (HI) distribution
arXiv 2607.24412 · 2026-09-30受限的佩龙包络与拟有界函数
Perron envelopes with globally bounded minorants
arXiv 2607.24139 · 2026-09-30有序结果的因果推断：一种贝叶斯解决方案
Is the treatment beneficial? Causal Inference with Ordinal Outcomes: A Bayesian Solution
arXiv 2607.23372 · 2026-09-30SIREN（诱使大语言模型陷入困境）：网页增强型大语言模型推荐系统中基于配对驱动的偏好操纵
SIREN (Luring LLMs onto the Rocks): PAIR-Driven Preference Manipulation in Web-RAG Recommenders
arXiv 2607.21951 · 2026-09-30模型条件下静态黑洞热力学的程函品质因子参数化
Photon sphere jet equivalence and the non-uniqueness of black-hole thermodynamics
arXiv 2607.20573 · 2026-09-30用于扩散模型的重要性感知OBS剪枝
Importance-Aware OBS Pruning for Diffusion Models
arXiv 2607.20048 · 2026-09-30大麦哲伦星系诱导的银河系晕扰动II：弥合场级推断与基于总结级模拟的推断
LMC-induced Perturbations in the Milky Way Halo II: Bridging Field-level Inference and Summary-level Simulation-Based Inference
arXiv 2607.20006 · 2026-09-30基于对称性的堆叠和扭曲二硫化钼双层中二次谐波产生的设计规则
Symmetry-Based Design Rules for Second-Harmonic Generation in Stacked and Twisted MoS2 Bilayers
arXiv 2607.19937 · 2026-09-30达尔文：为大语言模型安全评估与保护演化越狱对手及防护措施
DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection
arXiv 2607.19829 · 2026-09-30
