Instant research discovery
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
PreviousNext
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| A Safety-Bounded SDC-to-MCP Gateway for Medical AI Agents Bennet Gerlach, Stefan Fischer Published: 2026-09-25Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-25 | cs.DC | ai-safety, csdc, preprint | - | - |
| DynBranch: Speculative Subgraph Reuse for Dynamic Agentic LLM Serving Junyi Shen, Noppanat Wadlom, Yao Lu, Zhengyuan Su Published: 2026-09-25Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-25 | cs.DC | ai-safety, csdc, preprint | E13 / R11 (92%) | - |
| KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization Aheli Poddar, Arindam Samanta, Rohit Singh Rathaur, Sanskar Prasad Published: 2026-09-24Area: cs.DCCitations: 15 Tags: ai-safety, csdc, preprint | 2026-09-24 | cs.DC | ai-safety, csdc, preprint | E10 / R8 (93%) | 15 |
| Crossflow: Prefill-Decode Elasticity for Agentic LLM Serving Adnan Aziz, Ajit Mathews, Chunqiang Tang, Ehsan K. Ardestani Published: 2026-09-22Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-22 | cs.DC | ai-safety, csdc, preprint | E10 / R8 (90%) | - |
| EMA: Elastic and Performance Transparent Memory Across GPUs Ion Stoica, Tian Xia, Yi Xu Published: 2026-09-22Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-22 | cs.DC | ai-safety, csdc, preprint | E8 / R6 (91%) | - |
| Conduit: An Experience Data Plane for Distributed Reinforcement Learning Bo Zhao, Mario Di Francesco, Sitong Zhang, Tuo Shi Published: 2026-09-21Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-21 | cs.DC | ai-safety, csdc, preprint | - | - |
| MCP-GRANITE Benchmark: GRANularity Interface TEsting for MCP-Based LLM Agents Demetris Paschalides, George Pallis, Marios D. Dikaiakos, Moysis Symeonides Published: 2026-09-21Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-21 | cs.DC | ai-safety, csdc, preprint | E8 / R7 (90%) | - |
| Conflicting Pattern Formation by Teams of Anonymous, Fully Disoriented Robots Animesh Maiti, Prakhar Shukla, Subhash Bhagat Published: 2026-09-20Area: cs.DCCitations: 25 Tags: ai-safety, csdc, preprint | 2026-09-20 | cs.DC | ai-safety, csdc, preprint | E11 / R8 (96%) | 25 |
| Co-occurrence Patterns of LoRA Adapters in Production Diffusion Model Inference Services Bin Liao, Tao Zhang, Tao Zhou, Yanping Liu Published: 2026-09-20Area: cs.DCCitations: 37 Tags: ai-safety, csdc, preprint | 2026-09-20 | cs.DC | ai-safety, csdc, preprint | E12 / R10 (94%) | 37 |
| Accelerating Sharded Data Parallelism at Scale with Federated Learning Gianluca Mittone, Marco Aldinucci Published: 2026-09-17Area: cs.DCCitations: 1 Tags: ai-safety, csdc, preprint | 2026-09-17 | cs.DC | ai-safety, csdc, preprint | E8 / R8 (94%) | 1 |
| Detecting Soft Errors in Parallel Software with LLM-tuned Instruction Duplication Guanpeng Li, Yafan Huang Published: 2026-09-17Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-17 | cs.DC | ai-safety, csdc, preprint | E9 / R7 (91%) | - |
| How Much of a Real Workload Can LLM-Generated GPU Kernels Actually Reach? Ashish Garg, Gaurav Agarwal, Isha Singhal Published: 2026-09-17Area: cs.DCCitations: 10 Tags: ai-safety, csdc, preprint | 2026-09-17 | cs.DC | ai-safety, csdc, preprint | E12 / R8 (95%) | 10 |
| Ask the Tool, Don't Guess: Agent Tool Calls Hold Their Progress, and the Serving System Should Read It Feifei Li, Huanchen Zhang, Yingqiang Zhang, Yipeng Liu Published: 2026-09-16Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-16 | cs.DC | ai-safety, csdc, preprint | E10 / R7 (91%) | - |
| CIDERS: Cloud-Edge LLM Collaborative Learning via Accelerating Personalized Bilevel Optimization Hairui Yu, Hong Yan, Stella K. Chung, Victor H. Chen Published: 2026-09-14Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-14 | cs.DC | ai-safety, csdc, preprint | - | - |
| Cognitive Admission Control: Risk-Conditioned Assurance for Consequential Actions in Agentic Distributed Systems Deying Yu, Jun He Published: 2026-09-14Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-14 | cs.DC | ai-safety, csdc, preprint | - | - |
| Scalability and Performance Evaluation of Federated Learning Frameworks: A Comparative Analysis Ahmed Kubba, Bassel Soudan, Manar Wasif Abu Talib, Qassim Nasir Published: 2026-09-14Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint, safety-evaluation | 2026-09-14 | cs.DC | ai-safety, csdc, preprint, safety-evaluation | - | - |
| Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCache Frank Li Published: 2026-09-14Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-14 | cs.DC | ai-safety, csdc, preprint | - | - |
| ECAS: An Edge-Controlled Agentic System for Validation-Gated Scientific Application Execution Baixi Sun, Huihuo Zheng, Mingze Xia Published: 2026-09-13Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-13 | cs.DC | ai-safety, csdc, preprint | E11 / R11 (93%) | - |
| MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networks Iakovos S. Venieris, Leonidas Malachias, Sokratis Nikolaidis, Stylianos I. Venieris Published: 2026-09-13Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-13 | cs.DC | ai-safety, csdc, preprint | - | - |
| OpWeave: Flexible Operator Disaggregation for Heterogeneous LLM Serving Mengdi Wu, Rashmi Vinayak, Shiqi Pan, Shuhuai Lin Published: 2026-09-13Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-13 | cs.DC | ai-safety, csdc, preprint | E10 / R9 (91%) | - |
| TriCalRAG: A Three-Strategy, Retrieval-Augmented Benchmark for On-Premise LLM-Based Root Cause Analysis in AIOps Jeenal Chaudhary, Rohit Patel, Susil Kumar Mohanty Published: 2026-09-13Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-13 | cs.DC | ai-safety, csdc, preprint | - | - |
| mKernel: Fast Multi-GPU, Multi-Node Fused Kernels Costin Raiciu, Ion Stoica, Scott Shenker, Shawn Wei Chew Published: 2026-09-11Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-11 | cs.DC | ai-safety, csdc, preprint | E11 / R11 (93%) | - |
| RoofLang: Enabling AI-Driven Architecting of LLM Inference Systems Lei Qu, Peng Cheng, Yuting Jiang, Ziyue Yang Published: 2026-09-11Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-11 | cs.DC | ai-safety, csdc, preprint | E11 / R10 (93%) | - |
| GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replay Boning Li, Longbo Huang Published: 2026-09-10Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-10 | cs.DC | ai-safety, csdc, preprint | E7 / R5 (94%) | - |
| Avatar: Toward Autonomous End-to-End Orchestration of Scientific Workflows using LLMs Hai Duc Nguyen, Haochen Pan, Ian Foster, Kyle Chard Published: 2026-09-09Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-09 | cs.DC | ai-safety, csdc, preprint | E9 / R9 (92%) | - |
| A Measurement Study of LLM Inference Trade-offs Across Edge Continuum Hardware Demetris Trihinas, George Pallis, Marios D. Dikaiakos, Maysam Khatib Published: 2026-09-08Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-08 | cs.DC | ai-safety, csdc, preprint | E13 / R10 (94%) | - |
| Smart Adaptive Computing Across the Continuum: LLMs in IoT-Edge-Cloud Resource Management Antonino Vaccarella, Lanpei Li, Massimo Coppola, Vincenzo Lomonaco Published: 2026-09-08Area: cs.DCCitations: 15 Tags: ai-safety, csdc, preprint | 2026-09-08 | cs.DC | ai-safety, csdc, preprint | E15 / R14 (95%) | 15 |
| PLATOS: A Power and Latency-Aware Task-Oriented Scheduling Strategy for Healthcare IoT in Fog Computing Mohammed Alaa Ala'anzy, Zhanar Mukash, Zulfiqar Ahmad Published: 2026-09-07Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-07 | cs.DC | ai-safety, csdc, preprint | E10 / R9 (90%) | - |
| Diamond Agent: Agentic Control of Federated HPC Resources as a Service Haotian Xie, Ian Foster, Junlin Chen, Kyle Chard Published: 2026-09-05Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-05 | cs.DC | ai-safety, csdc, preprint | E11 / R9 (91%) | - |
| Atlas: Optimizing Deployment of Compound AI Workflows on Heterogeneous Clusters Andrija Stanisic, Milos Gravara, Stefan Nastic Published: 2026-09-03Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-09-03 | cs.DC | ai-safety, csdc, preprint | E9 / R6 (94%) | - |