{"total":61,"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":"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":"2510.26144","title":"The FM Agent","created":"2025-10-30","cited_by_count":21,"area":"agents"},{"id":"2603.21331","title":"AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search","created":"2026-03-22","cited_by_count":18,"area":null},{"id":"2510.03760","title":"EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models","created":"2025-10-04","cited_by_count":13,"area":null},{"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":"2602.14293","title":"KernelBlaster: Continual Cross-Task CUDA Optimization via Memory-Augmented In-Context Reinforcement Learning","created":"2026-02-15","cited_by_count":12,"area":"lr"},{"id":"2508.20258","title":"SwizzlePerf: Hardware-Aware LLMs for GPU Kernel Performance Optimization","created":"2025-08-27","cited_by_count":11,"area":null},{"id":"2509.08269","title":"A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving","created":"2025-09-10","cited_by_count":11,"area":null},{"id":"2603.10085","title":"KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization","created":"2026-03-10","cited_by_count":11,"area":"agents"},{"id":"2603.02236","title":"CUDABench: Benchmarking LLMs for Text-to-CUDA Generation","created":"2026-02-13","cited_by_count":10,"area":null},{"id":"2606.08960","title":"Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops","created":"2026-06-08","cited_by_count":9,"area":"agents"},{"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":"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":"2604.01489","title":"CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe","created":"2026-04-01","cited_by_count":6,"area":"agents"},{"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":"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":"2603.07169","title":"Making LLMs Optimize Multi-Scenario CUDA Kernels Like Experts","created":"2026-03-07","cited_by_count":4,"area":null},{"id":"2604.02721","title":"GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning","created":"2026-04-03","cited_by_count":4,"area":"agents"},{"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":"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":"2605.23215","title":"FastKernels: Benchmarking GPU Kernel Generation in Production","created":"2026-05-22","cited_by_count":3,"area":"agents"},{"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":"2605.05023","title":"CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels","created":"2026-05-06","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":"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":"2605.29357","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":"2508.02091","title":"CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search","created":"2025-08-04","cited_by_count":0,"area":"lr"},{"id":"2601.02045","title":"The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2603.13019","title":"ARL-Tangram: Unleash the Resource Efficiency in Agentic Reinforcement Learning","created":"2026-03-13","cited_by_count":0,"area":"agents"},{"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":"2605.26720","title":"Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation","created":"2026-05-26","cited_by_count":0,"area":"agents"},{"id":"2605.28213","title":"Learning When to Optimize: Verified Optimization Skills from Expert GPU-Kernel Lineages","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"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":"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":"2607.27271","title":"RLPF: Reinforcement Learning from Performance Feedback for Code Generation","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.01804","title":"LEAP: Lean Environment-Feedback via Adaptive Pruning for Code RL in GPU Kernel Generation","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.12700","title":"A Contract-Grade Verifier for LLM-Generated GPU Kernels, and a Native Blackwell Backward for the Gated-Linear-Recurrence Family","created":"2026-08-13","cited_by_count":0,"area":null},{"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":"2608.21836","title":"LLM4LLM: Bridging Kernel Benchmarks and Real Deployment via Closed-Loop Agentic Optimization","created":"2026-08-22","cited_by_count":0,"area":"agents"},{"id":"2609.00058","title":"CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language","created":"2026-08-30","cited_by_count":0,"area":"agents"},{"id":"2609.35568","title":"From Experience to Expertise: Adoption-Aware Memory Learning for Data-Scarce NPU Kernel Synthesis","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38757","title":"Self-Evolving Algorithm-Design Agents: Escaping In-Context Evolutionary Stagnation via Population-Curated Policy Optimization","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.05014","title":"MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}