Cover Image

Kevin: Multi-Turn RL for Generating CUDA Kernels

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Baronio, Carlo, Marsella, Pietro, Pan, Ben, Guo, Simon, Alberti, Silas
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Performance Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

KernelBench: Can LLMs Write Efficient GPU Kernels?
by: Ouyang, Anne, et al.
Published: (2025)

GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimization
by: Andrews, Martin, et al.
Published: (2025)

VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations
by: Zheng, Zhongchun, et al.
Published: (2025)

Lookup multivariate Kolmogorov-Arnold Networks
by: Pozdnyakov, Sergey, et al.
Published: (2025)

Learning Performance-Improving Code Edits
by: Shypula, Alexander, et al.
Published: (2023)

AI-driven Java Performance Testing: Balancing Result Quality with Testing Time
by: Traini, Luca, et al.
Published: (2024)

Predicting Configuration Performance in Multiple Environments with Sequential Meta-learning
by: Gong, Jingzhi, et al.
Published: (2024)

Enhancing Energy-Awareness in Deep Learning through Fine-Grained Energy Measurement
by: Rajput, Saurabhsingh, et al.
Published: (2023)

LLM-Vectorizer: LLM-based Verified Loop Vectorizer
by: Taneja, Jubi, et al.
Published: (2024)

Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
by: Lange, Robert Tjarko, et al.
Published: (2025)

CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe
by: Saba, Tara, et al.
Published: (2026)

MultiKernelBench: A Multi-Platform Benchmark for Kernel Generation
by: Wen, Zhongzhen, et al.
Published: (2025)

KForge: Program Synthesis for Diverse AI Hardware Accelerators
by: Sereda, Taras, et al.
Published: (2025)

Performance Prediction for Large Systems via Text-to-Text Regression
by: Akhauri, Yash, et al.
Published: (2025)

Regression Language Models for Code
by: Akhauri, Yash, et al.
Published: (2025)

Enabling Performant and Flexible Model-Internal Observability for LLM Inference
by: Yu, Nengneng, et al.
Published: (2026)

CDS4RAG: Cyclic Dual-Sequential Hyperparameter Optimization for RAG
by: Chen, Pengzhou, et al.
Published: (2026)

LLMSYS-HPOBench: Hyperparameter Optimization Benchmark Suite for Real-World LLM Systems
by: Wu, Siyu, et al.
Published: (2026)

Worst-Case Convergence Time of ML Algorithms via Extreme Value Theory
by: Tizpaz-Niari, Saeid, et al.
Published: (2024)

Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation
by: Chen, Ziru, et al.
Published: (2026)

DeepGD: A Multi-Objective Black-Box Test Selection Approach for Deep Neural Networks
by: Aghababaeyan, Zohreh, et al.
Published: (2023)

SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?
by: Ma, Jeffrey Jian, et al.
Published: (2025)

PerfBench: Can Agents Resolve Real-World Performance Bugs?
by: Garg, Spandan, et al.
Published: (2025)

Prompting for Performance: Exploring LLMs for Configuring Software
by: Spieker, Helge, et al.
Published: (2025)

Interpreting Performance Profiles with Deep Learning
by: Liu, Zhuoran
Published: (2025)

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software
by: Yi, Lirong, et al.
Published: (2025)

Can We Make Code Green? Understanding Trade-Offs in LLMs vs. Human Code Optimizations
by: Rani, Pooja, et al.
Published: (2025)

Energy Consumption of Dataframe Libraries for End-to-End Deep Learning Pipelines:A Comparative Analysis
by: Kumar, Punit, et al.
Published: (2025)

Root Cause Localization for Microservice Systems in Cloud-edge Collaborative Environments
by: Zhu, Yuhan, et al.
Published: (2024)

Predicting Software Performance with Divide-and-Learn
by: Gong, Jingzhi, et al.
Published: (2023)

On the Compression of Language Models for Code: An Empirical Study on CodeBERT
by: d'Aloisio, Giordano, et al.
Published: (2024)

Should AI Optimize Your Code? A Comparative Study of Classical Optimizing Compilers Versus Current Large Language Models
by: Rosas, Miguel Romero, et al.
Published: (2024)

This Is Taking Too Long -- Investigating Time as a Proxy for Energy Consumption of LLMs
by: Krupp, Lars, et al.
Published: (2026)

Automatic Generation of High-Performance RL Environments
by: Karten, Seth, et al.
Published: (2026)

Prefetching Cache Optimization Using Graph Neural Networks: A Modular Framework and Conceptual Analysis
by: Qowy, F. I.
Published: (2025)

Risk-Aware Batch Testing for Performance Regression Detection
by: Sayedsalehi, Ali, et al.
Published: (2026)

Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
by: Li, Xu, et al.
Published: (2026)

AscendCraft: Automatic Ascend NPU Kernel Generation via DSL-Guided Transcompilation
by: Wen, Zhongzhen, et al.
Published: (2026)

Assuring the Safety of Reinforcement Learning Components: AMLAS-RL
by: Imrie, Calum Corrie, et al.
Published: (2025)

OptiML: An End-to-End Framework for Program Synthesis and CUDA Kernel Optimization
by: Bhattacharjee, Arijit, et al.
Published: (2026)