{"total":225,"rows":[{"id":"2507.02825","title":"Establishing Best Practices for Building Rigorous Agentic Benchmarks","created":"2025-07-03","cited_by_count":102,"area":"agents"},{"id":"2507.14111","title":"CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning","created":"2025-07-18","cited_by_count":61,"area":"lr"},{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59,"area":null},{"id":"2509.14279","title":"Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization","created":"2025-09-16","cited_by_count":56,"area":"lr"},{"id":"2510.06189","title":"Barbarians at the Gate: How AI is Upending Systems Research","created":"2025-10-07","cited_by_count":54,"area":null},{"id":"2604.01658","title":"CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery","created":"2026-04-02","cited_by_count":52,"area":"agents"},{"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":"2507.05687","title":"AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs","created":"2025-07-08","cited_by_count":40,"area":null},{"id":"2506.09092","title":"CUDA-LLM: LLMs Can Write Efficient CUDA Kernels","created":"2025-06-10","cited_by_count":34,"area":null},{"id":"2605.21384","title":"SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents","created":"2026-05-20","cited_by_count":28,"area":"agents"},{"id":"2507.15887","title":"AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2510.16996","title":"STARK: Strategic Team of Agents for Refining Kernels","created":"2025-10-19","cited_by_count":25,"area":"agents"},{"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":"2512.15699","title":"FrontierCS: Evolving Challenges for Evolving Intelligence","created":"2025-12-17","cited_by_count":23,"area":null},{"id":"2506.20807","title":"GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimization","created":"2025-06-25","cited_by_count":22,"area":null},{"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":"2602.15112","title":"ResearchGym: Evaluating Language Model Agents on Real-World AI Research","created":"2026-02-16","cited_by_count":22,"area":"agents"},{"id":"2511.06090","title":"SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?","created":"2025-11-08","cited_by_count":21,"area":null},{"id":"2604.19341","title":"Structured Scaling of AI Discovery Across Diverse Scientific Domains","created":"2026-04-21","cited_by_count":21,"area":null},{"id":"2511.20100","title":"QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation","created":"2025-11-25","cited_by_count":19,"area":"lr"},{"id":"2603.19173","title":"SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits","created":"2026-03-19","cited_by_count":18,"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":"2609.14858","title":"Dream-RSI: Recursive Self-Improvement through Evolving Worlds","created":"2026-09-14","cited_by_count":18,"area":null},{"id":"2603.24511","title":"Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs","created":"2026-03-25","cited_by_count":17,"area":"safety"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2605.12673","title":"Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack","created":"2026-05-12","cited_by_count":14,"area":null},{"id":"2505.18574","title":"Autocomp: A Powerful and Portable Code Optimizer for Tensor Accelerators","created":"2025-05-24","cited_by_count":13,"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":"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":"2512.12216","title":"Training Versatile Coding Agents in Synthetic Environments","created":"2025-12-13","cited_by_count":13,"area":"agents"},{"id":"2603.12440","title":"KernelFoundry: Hardware-aware evolutionary GPU kernel optimization","created":"2026-03-12","cited_by_count":13,"area":null},{"id":"2606.05080","title":"AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?","created":"2026-06-03","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":"2605.04956","title":"KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels","created":"2026-05-06","cited_by_count":12,"area":null},{"id":"2605.26079","title":"Automated Benchmark Auditing for AI Agents and Large Language Models","created":"2026-05-25","cited_by_count":12,"area":"agents"},{"id":"2508.20258","title":"SwizzlePerf: Hardware-Aware LLMs for GPU Kernel Performance Optimization","created":"2025-08-27","cited_by_count":11,"area":null},{"id":"2511.06345","title":"PRAGMA: A Profiling-Reasoned Multi-Agent Framework for Automatic Kernel Optimization","created":"2025-11-09","cited_by_count":11,"area":"lr"},{"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":"2605.18661","title":"AI for Auto-Research: Roadmap & User Guide","created":"2026-05-18","cited_by_count":11,"area":null},{"id":"2608.20318","title":"AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement","created":"2026-08-20","cited_by_count":11,"area":"agents"},{"id":"2609.26457","title":"Recursive self-improvement of AI research agents","created":"2026-09-22","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":"2511.12294","title":"ProofWright: Towards Agentic Formal Verification of CUDA","created":"2025-11-15","cited_by_count":9,"area":"agents"},{"id":"2606.08960","title":"Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops","created":"2026-06-08","cited_by_count":9,"area":"agents"},{"id":"2608.06301","title":"HarnessOpt-Bench: Evaluating LLMs at Harness Optimization","created":"2026-08-06","cited_by_count":9,"area":"agents"},{"id":"2504.21187","title":"LIFT: LLM-Based Pragma Insertion for HLS via GNN Supervised Fine-Tuning","created":"2025-04-29","cited_by_count":8,"area":null},{"id":"2603.13428","title":"SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution","created":"2026-03-13","cited_by_count":8,"area":null},{"id":"2603.23994","title":"Understanding the Challenges in Iterative Generative Optimization with LLMs","created":"2026-03-25","cited_by_count":8,"area":null},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2607.16241","title":"KernelBench-Verified: Do LLM-Generated Kernels Actually Beat PyTorch?","created":"2026-06-26","cited_by_count":8,"area":null},{"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":"2607.07847","title":"When Does Continual Learning Require Learning","created":"2026-07-08","cited_by_count":7,"area":"inference"},{"id":"2505.11480","title":"SuperCoder: Assembly Program Superoptimization with Large Language Models","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2508.07932","title":"\\(X\\)-evolve: Solution space evolution powered by large language models","created":"2025-08-11","cited_by_count":6,"area":null},{"id":"2602.16819","title":"Hybrid-Gym: Training Coding Agents to Generalize Across Tasks","created":"2026-02-18","cited_by_count":6,"area":"agents"},{"id":"2602.19594","title":"ISO-Bench: Can Coding Agents Optimize Real-World Inference Workloads?","created":"2026-02-23","cited_by_count":6,"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":"2606.13662","title":"EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery","created":"2026-06-11","cited_by_count":6,"area":"agents"},{"id":"2606.20128","title":"The Correctness Illusion in LLM-Generated GPU Kernels","created":"2026-06-18","cited_by_count":6,"area":null},{"id":"2606.29082","title":"Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks","created":"2026-06-27","cited_by_count":6,"area":null},{"id":"2606.30182","title":"MirrorCode: AI can rebuild entire programs from behavior alone","created":"2026-06-29","cited_by_count":6,"area":null},{"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":"2602.06107","title":"Jackpot: Optimal Budgeted Rejection Sampling for Extreme Actor-Policy Mismatch Reinforcement Learning","created":"2026-02-05","cited_by_count":5,"area":"lr"},{"id":"2603.08721","title":"KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware","created":"2026-02-10","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":"2604.19440","title":"What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search","created":"2026-04-21","cited_by_count":5,"area":"agents"},{"id":"2605.19269","title":"CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs","created":"2026-05-19","cited_by_count":5,"area":null},{"id":"2607.20468","title":"InferenceBench: A Benchmark for Open-Ended LLM Inference Optimization by AI Agents","created":"2026-05-20","cited_by_count":5,"area":"agents"},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2506.11058","title":"Refactoring Codebases through Library Design","created":"2025-05-26","cited_by_count":4,"area":null},{"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":"2605.06068","title":"VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2606.26453","title":"Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization","created":"2026-06-24","cited_by_count":4,"area":null},{"id":"2609.04280","title":"EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?","created":"2026-09-03","cited_by_count":4,"area":"agents"},{"id":"2505.02184","title":"Leveraging LLMs to Automate Energy-Aware Refactoring of Parallel Scientific Codes","created":"2025-05-04","cited_by_count":3,"area":null},{"id":"2511.13274","title":"KForge: Program Synthesis for Diverse AI Hardware Accelerators","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2512.22147","title":"GPU Kernel Optimization Beyond Full Builds: An LLM Framework with Minimal Executable Programs","created":"2025-12-15","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":"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":"2603.20075","title":"Agentic Harness for Real-World Compilers","created":"2026-03-20","cited_by_count":3,"area":"agents"},{"id":"2603.21465","title":"DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation","created":"2026-03-23","cited_by_count":3,"area":"lr"},{"id":"2603.23566","title":"AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2604.08590","title":"AlphaLab: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs","created":"2026-03-31","cited_by_count":3,"area":"agents"},{"id":"2604.11072","title":"Hodoscope: Unsupervised Monitoring for AI Misbehaviors","created":"2026-04-13","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}],"next_cursor":"100"}