Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
Anzeige
Ähnliche Artikel
arXiv – cs.LG
•
CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization
arXiv – cs.AI
•
Neue Studie deckt stille Fehler in Multi-Agenten‑AI auf
arXiv – cs.AI
•
QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code
arXiv – cs.AI
•
LLM-Tester CLAUSE: Benchmark zur Erkennung von Vertragsfehlern
arXiv – cs.AI
•
Mechanics of Learned Reasoning 1: TempoBench, A Benchmark for Interpretable Deconstruction of Reasoning System Performance
arXiv – cs.AI
•
APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Training