001 Specula: Scaling formal specifications for autonomous model checking of system code arXiv Paper Q. Cheng, Saad Mohammad Rafid Pial et al. 3 days ago 002 Defining AI-Native Systems: Autonomy as Revision Authority arXiv Paper Cheng Tan Jul 22 003 Isolation Failure From Shared Storage: Characterizing and Exploiting Page-Cache SCA Leakage Across Containers and VMs arXiv Paper Alon Abudraham, Xingyu Chen et al. Jul 20 004 TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization arXiv Paper Alex Mathai, Shobini Iyer et al. Jul 20 005 WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning arXiv Paper Ryan Xu, Atlas Zhao et al. Jul 19 006 ExaGEMM: Exploration Framework for CPU-Driven ML Inference via Associative In-Register Computing for Low-Bit GEMM arXiv Paper Hyunwoo Oh, Suyeon Jang et al. Jul 16 007 PolyQ: Codesigning End-to-End Quantization Framework for Scalable Edge CPU LLM Inference arXiv Paper Hyunwoo Oh, Suyeon Jang et al. Jul 16 008 Complets: Universal Compartmentalisation and Programming Model For Arm Permission Overlay Extension 2 arXiv Paper V. Sartakov Jul 6 009 Elastic Gang: Per-Token Membership Change for a Hard-Barriered LLM Inference Gang Co-Scheduled with OS Processes arXiv Paper Da-Hyun Son Jul 6 010 Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots arXiv Paper Ling Xu et al. Jul 2 011 Fine-Grained Computation Offload for Off-the-Shelf Servers in Tens of Lines arXiv Paper Bojie Li Jul 2 012 EnclaveX: End-to-End Confidential AI with CPU/GPU TEEs arXiv Paper Robert Schambach, Quoc Do Le et al. Jun 30 013 LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents arXiv Paper Yogeswar Reddy Thota Jun 29 014 Kops: Safely Extending the eBPF Compilation Pipeline with Native Operations arXiv Paper Yusheng Zheng, Zhengjie Ji et al. Jun 23 015 AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction arXiv Paper Shanhui Zhao, Jiacheng Liu et al. Jun 22 016 EnerInfer: Energy-Aware On-Device LLM Inference arXiv Paper Bohua Zou, Nian Liu et al. Jun 22 017 FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation arXiv Paper Yin Wu, Yitong Chen et al. Jun 22 018 AgenticOS: An Intent-Oriented Secure Operating System Architecture for Autonomous AI Agents arXiv Paper Zhen Zhao, Yu Zhang et al. Jun 19 019 CloakLM: Obfuscating GPU Memory Layout to Mitigate Model Ex-filtration for Serving arXiv Paper Kunal Jain, Seokjin Go et al. Jun 16 020 Cordon: Semantic Transactions for Tool-Using LLM Agents arXiv Paper Zheng Chen, Hanqing Liu et al. Jun 16 021 FMplex: Model Virtualization for Serving Extensible Foundation Models arXiv Paper Hetvi Shastri, Pragya Sharma et al. Jun 8 022 Policy Description Language for Authorization using Logic-Based Programming arXiv Paper Masaki Hashimoto, Mira Kim et al. Jun 6 023 TOMOYO Linux: A Mandatory Access Control Method Based on Application Execution State arXiv Paper Toshiharu Harada, T. Handa et al. Jun 6 024 AgileOS: A GPU Operating System Layer for Protected CUDA Services arXiv Paper Zhuoping Yang, Yiyu Shi et al. Jun 4 025 Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents arXiv Paper Yingqi Zhang Jun 2 026 Beyond Edge Coverage: Per-Task Data-Flow Extraction at Kernel Function Boundaries via LLVM arXiv Paper Yunseong Kim May 30 027 Edge-Based QoS-Aware Adaptive Task Placement: A Closed-Loop Control in Multi-Robot Systems arXiv Paper Thien Tran et al. May 30 028 A Secure, Manifest-Based Framework for Delegated Privilege Promotion arXiv Paper R. Chowdhury, A. Shah May 27 029 Patchlings: Safety-Preserving Flash-Based Hotpatching for Automotive Microcontrollers arXiv Paper Y. Liu, Sekar Kulandaivel et al. May 27 030 LearnedCache: An eBPF-Integrated Perceptron-Based Eviction Policy for the Linux Page Cache arXiv Paper Ze Qi May 25 031 Sandlock: Confining AI Agent Code with Unprivileged Linux Primitives arXiv Paper Cong Wang, Yusheng Zheng May 25 032 DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback arXiv Paper Yunpeng Dong, Jingkai He et al. May 21 033 TClone: Low-Latency Forking of Live GUI Environments for Computer-Use Agents arXiv Paper Yutong Huang, Vikranth Srivatsa et al. May 17 034 Skim: Speculative Execution for Fast and Efficient Web Agents arXiv Paper Mike Wong, Kevin Hsieh et al. May 15 035 TuxBot: Semantic-Aware Online OS Tuning with Large Language Models arXiv Paper Georgios Liargkovas, Mihir Joshi et al. May 14 036 It's Not the Size: Harness Design Determines Operational Stability in Small Language Models arXiv Paper Yongkyu Cho May 12 037 KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving arXiv Paper Zhiqing Zhong, Zhijing Ye et al. May 10 038 Pomegranate: A Lightweight Compartmentalization Architecture using Virtualization Extensions arXiv Paper Shriram Raja et al. May 7 039 ipc_shared_ptr: A Publish/Subscribe-Aware Smart Pointer for Cross-Process Object Lifetime Management arXiv Paper Takahiro Ishikawa-Aso et al. May 5 040 VUDA: Breaking CUDA-Vulkan Isolation for Spatial Sharing of Compute and Graphics on the Same GPU arXiv Paper Bin Xu, Pengfei Hu et al. May 2 041 SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters arXiv Paper Dongxing Guo, Jikun Wu et al. May 1 042 Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes arXiv Paper Tianyuan Wu, Chaokun Chang et al. Apr 30 043 An AI Agent Execution Environment to Safeguard User Data arXiv Paper Robert Stanley, Avirishu Verma et al. Apr 21 044 Scheduling Analysis of UAV Flight Control Workloads on PREEMPT_RT Linux Using a Raspberry Pi 5 arXiv Paper Luiz Giacomossi et al. Apr 21 045 AgenTEE: Confidential LLM Agent Execution on Edge Devices arXiv Paper Sina Abdollahi, M. Maheri et al. Apr 20 046 Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives arXiv Paper Da-Hyun Son Apr 18 047 A Physics-Aware Framework for Short-Term GPU Power Forecasting of AI Data Centers arXiv Paper M. Saleh, Sanjay Chawla et al. Apr 14 048 MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems arXiv Paper Yifei Wang, Hancheng Ye et al. Apr 14 049 ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems arXiv Paper Da-Hyun Son Apr 13 050 ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents arXiv Paper Mofasshara Rafique, Laurent Bindschaedler Apr 11 051 A Hardware-Anchored Privacy Middleware for PII Sharing Across Heterogeneous Embedded Consumer Devices arXiv Paper Aditya Sabbineni et al. Apr 9 052 VCAO: Verifier-Centered Agentic Orchestration for Strategic OS Vulnerability Discovery arXiv Paper Suyash Mishra Apr 9 053 Blink: CPU-Free LLM Inference by Delegating the Serving Stack to GPU and SmartNIC arXiv Paper Mohammad Siavashi, Mariano Scazzariello et al. Apr 8 054 MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU arXiv Paper Zhengqing Yuan, Hanchi Sun et al. Apr 6 055 Generative Profiling for Soft Real-Time Systems and its Applications to Resource Allocation arXiv Paper Georgiy A. Bondar, Abby Eisenklam et al. Apr 1 056 StepCache: Step-Level Reuse with Lightweight Verification and Selective Patching for LLM Serving arXiv Paper Azam Nouri Mar 24 057 Tock: From Research to Securing 10 Million Computers arXiv Paper Leon Schuermann et al. Mar 23 058 Brain-inspired AI for Edge Intelligence: a systematic review arXiv Paper Yingchao Cheng, Mei-Yu Wang et al. Mar 19 059 FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation arXiv Paper Yin Wu, Yitong Chen et al. Mar 10 060 The Missing Memory Hierarchy: Demand Paging for LLM Context Windows arXiv Paper Tony Mason Mar 9