{"total":78,"rows":[{"id":"2509.07506","title":"Astra: A Multi-Agent System for GPU Kernel Performance Optimization","created":"2025-09-09","cited_by_count":51,"area":"agents"},{"id":"2602.24286","title":"CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation","created":"2026-02-27","cited_by_count":47,"area":"agents"},{"id":"2511.01884","title":"CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization","created":"2025-10-23","cited_by_count":45,"area":"agents"},{"id":"2507.17773","title":"MultiKernelBench: A Multi-Platform Benchmark for Kernel Generation","created":"2025-07-20","cited_by_count":38,"area":null},{"id":"2601.00227","title":"FlashInfer-Bench: Building the Virtuous Cycle for AI-driven LLM Systems","created":"2026-01-01","cited_by_count":25,"area":null},{"id":"2510.17891","title":"TritonRL: Training LLMs to Think and Code Triton Without Cheating","created":"2025-10-18","cited_by_count":24,"area":"lr"},{"id":"2602.19128","title":"K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model","created":"2026-02-22","cited_by_count":24,"area":"wm"},{"id":"2511.15915","title":"AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization","created":"2025-11-19","cited_by_count":23,"area":"agents"},{"id":"2602.05885","title":"Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations","created":"2026-02-05","cited_by_count":22,"area":"lr"},{"id":"2510.07356","title":"ConCuR: Conciseness Makes State-of-the-Art Kernel Generation","created":"2025-10-08","cited_by_count":13,"area":"lr"},{"id":"2512.02551","title":"CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning","created":"2025-12-02","cited_by_count":13,"area":"lr"},{"id":"2603.12440","title":"KernelFoundry: Hardware-aware evolutionary GPU kernel optimization","created":"2026-03-12","cited_by_count":13,"area":null},{"id":"2508.20258","title":"SwizzlePerf: Hardware-Aware LLMs for GPU Kernel Performance Optimization","created":"2025-08-27","cited_by_count":11,"area":null},{"id":"2509.25084","title":"Scaling Generalist Data-Analytic Agents","created":"2025-09-29","cited_by_count":11,"area":"agents"},{"id":"2601.15727","title":"Towards Automated Kernel Generation in the Era of LLMs","created":"2026-01-22","cited_by_count":11,"area":"agents"},{"id":"2603.10085","title":"KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization","created":"2026-03-10","cited_by_count":11,"area":"agents"},{"id":"2510.19873","title":"From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph","created":"2025-10-22","cited_by_count":10,"area":"lr"},{"id":"2606.08960","title":"Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops","created":"2026-06-08","cited_by_count":9,"area":"agents"},{"id":"2603.23994","title":"Understanding the Challenges in Iterative Generative Optimization with LLMs","created":"2026-03-25","cited_by_count":8,"area":null},{"id":"2512.16465","title":"cuPilot: A Strategy-Coordinated Multi-agent Framework for CUDA Kernel Evolution","created":"2025-12-18","cited_by_count":7,"area":"agents"},{"id":"2512.23424","title":"AKG kernel Agent: A Multi-Agent Framework for Cross-Platform Kernel Synthesis","created":"2025-12-29","cited_by_count":7,"area":"agents"},{"id":"2601.22760","title":"AscendCraft: Automatic Ascend NPU Kernel Generation via DSL-Guided Transcompilation","created":"2026-01-30","cited_by_count":7,"area":null},{"id":"2603.02637","title":"StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning","created":"2026-03-03","cited_by_count":7,"area":"agents"},{"id":"2603.28342","title":"Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization","created":"2026-03-30","cited_by_count":6,"area":null},{"id":"2510.16552","title":"LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs","created":"2025-10-18","cited_by_count":5,"area":"synth"},{"id":"2512.23236","title":"KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta","created":"2025-12-29","cited_by_count":5,"area":"agents"},{"id":"2603.29010","title":"Improving Efficiency of GPU Kernel Optimization Agents using a Domain-Specific Language and Speed-of-Light Guidance","created":"2026-03-30","cited_by_count":5,"area":"agents"},{"id":"2511.16964","title":"Optimizing PyTorch Inference with LLM-Based Multi-Agent Systems","created":"2025-11-21","cited_by_count":4,"area":"agents"},{"id":"2601.05475","title":"MaxCode: A Max-Reward Reinforcement Learning Framework for Automated Code Optimization","created":"2026-01-09","cited_by_count":4,"area":"alignment"},{"id":"2602.11000","title":"Fine-Tuning GPT-5 for GPU Kernel Generation","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2603.07169","title":"Making LLMs Optimize Multi-Scenario CUDA Kernels Like Experts","created":"2026-03-07","cited_by_count":4,"area":null},{"id":"2604.03144","title":"InCoder-32B-Thinking: Industrial Code World Model for Thinking","created":"2026-04-03","cited_by_count":4,"area":"lr"},{"id":"2512.14018","title":"PerfCoder: Large Language Models for Interpretable Code Performance Optimization","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2602.11715","title":"DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2602.12305","title":"OptiML: An End-to-End Framework for Program Synthesis and CUDA Kernel Optimization","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2602.15898","title":"MultiCube-RAG for Multi-hop Question Answering","created":"2026-02-11","cited_by_count":3,"area":null},{"id":"2603.10846","title":"Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2603.23566","title":"AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2604.16625","title":"AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2605.08756","title":"AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design","created":"2026-05-09","cited_by_count":3,"area":"agents"},{"id":"2605.23215","title":"FastKernels: Benchmarking GPU Kernel Generation in Production","created":"2026-05-22","cited_by_count":3,"area":"agents"},{"id":"2609.02987","title":"Tail-Likelihood Reinforcement Learning","created":"2026-09-02","cited_by_count":3,"area":"deeprl"},{"id":"2511.18868","title":"KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed Bandits","created":"2025-11-24","cited_by_count":2,"area":"inference"},{"id":"2603.02376","title":"CUCo: An Agentic Framework for Compute and Communication Co-design","created":"2026-03-02","cited_by_count":2,"area":"agents"},{"id":"2605.26118","title":"Xe-Forge: Multi-Stage LLM-Powered Kernel Optimization for Intel GPU","created":"2026-04-16","cited_by_count":2,"area":null},{"id":"2606.04847","title":"MusaCoder: Native GPU Kernel Generation with Full-Stack Training on Moore Threads GPU","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2509.14265","title":"Evolution of Kernels: Automated RISC-V Kernel Optimization with Large Language Models","created":"2025-09-14","cited_by_count":1,"area":null},{"id":"2511.08083","title":"HipKittens: Fast and Furious AMD Kernels","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2601.16480","title":"TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization","created":"2026-01-23","cited_by_count":1,"area":"lr"},{"id":"2602.07670","title":"Surprisal-Guided Selection: Compute-Optimal Test-Time Strategies for Execution-Grounded Code Generation","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2603.11935","title":"MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2605.08467","title":"CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.29357","title":"PassNet: Scaling Large Language Models for Graph Compiler Pass Generation","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.16231","title":"From Tokens to Regions: CUDA-Sensitive Instruction Tuning for GPU Kernel Generation","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2607.01590","title":"Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.18171","title":"FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications","created":"2026-07-20","cited_by_count":1,"area":"agents"},{"id":"2607.20501","title":"MKEvolve: A Modular Multi-Agent Framework for Kernel Code Generation","created":"2026-06-20","cited_by_count":1,"area":"agents"},{"id":"2607.20518","title":"CANN Bench: Benchmarking Agent Generated Kernels against Real NPU and Algorithmic Limits","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2608.25061","title":"DataKernelBench: Can LLMs Optimize Database Queries on GPUs?","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2603.13640","title":"SemRep: Generative Code Representation Learning with Code Transformations","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2605.08455","title":"CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.25954","title":"Step-TP: A Grounded, Step-Level Dataset with Chain-of-Thought Reasoning for LLM-Guided Tensor Program Optimization","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2605.30359","title":"Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.26758","title":"EGG: An Expert-Guided Agent Framework for Kernel Generation","created":"2026-06-25","cited_by_count":0,"area":"agents"},{"id":"2606.30442","title":"The FIL Hypothesis: Inductive Biases Help with Kernel Engineering","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.20908","title":"Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation","created":"2026-07-23","cited_by_count":0,"area":"lr"},{"id":"2607.23089","title":"Compiler-Grounded Hierarchical Diagnosis for LLM-Based Triton Kernel Optimization","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2607.27231","title":"KernelGenBench: Can LLMs and Agents Write Efficient Kernels Across Operator Sources and Hardware Platforms?","created":"2026-07-22","cited_by_count":0,"area":"agents"},{"id":"2608.02712","title":"Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Hardware Operators","created":"2026-08-03","cited_by_count":0,"area":"agents"},{"id":"2608.17379","title":"PTXBench: Benchmarking and Adapting LLMs for GPU Kernel Optimization with Architecture-specific PTX","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.21157","title":"HIERA: Workload-Aware Planning Across Implementation Spaces for GPU Kernel Optimization","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.12471","title":"AMDKernelVault: Large-Scale Datasets and Agentic Training for AMD GPU Kernel Optimization","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.19611","title":"The Output-Space Hypothesis: Enumerative Equivalence Checking for Tensor Programs","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.22220","title":"Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.26779","title":"CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents","created":"2026-09-22","cited_by_count":0,"area":"agents"},{"id":"2609.33074","title":"KernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.05014","title":"MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.15924","title":"Scalable Weak-to-Strong Verifier Hardening for Agent Environments","created":"2026-10-11","cited_by_count":0,"area":"agents"}],"next_cursor":null}