{"total":120,"rows":[{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59,"area":null},{"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":"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":"2507.15887","title":"AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?","created":"2025-07-19","cited_by_count":27,"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":"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":"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":"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":"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":"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":"2605.04956","title":"KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels","created":"2026-05-06","cited_by_count":12,"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":"2605.18661","title":"AI for Auto-Research: Roadmap & User Guide","created":"2026-05-18","cited_by_count":11,"area":null},{"id":"2603.02236","title":"CUDABench: Benchmarking LLMs for Text-to-CUDA Generation","created":"2026-02-13","cited_by_count":10,"area":null},{"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":"2607.16241","title":"KernelBench-Verified: Do LLM-Generated Kernels Actually Beat PyTorch?","created":"2026-06-26","cited_by_count":8,"area":null},{"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":"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":"2603.28342","title":"Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization","created":"2026-03-30","cited_by_count":6,"area":null},{"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":"2605.19269","title":"CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs","created":"2026-05-19","cited_by_count":5,"area":null},{"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":"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":"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":"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":"2603.23566","title":"AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization","created":"2026-03-24","cited_by_count":3,"area":null},{"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},{"id":"2605.14445","title":"FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale","created":"2026-05-14","cited_by_count":3,"area":null},{"id":"2606.16497","title":"daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization","created":"2026-06-15","cited_by_count":3,"area":null},{"id":"2607.14541","title":"Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent","created":"2026-07-16","cited_by_count":3,"area":null},{"id":"2607.19653","title":"PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2509.25203","title":"Generating High-Quality Datasets for Code Editing via Open-Source Language Models","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2512.14806","title":"Let the Barbarians In: How AI Can Accelerate Systems Performance Research","created":"2025-12-16","cited_by_count":2,"area":null},{"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":"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":"2605.29734","title":"HTAM: Hierarchical Transition-Attended Memory for Operator Optimization","created":"2026-05-28","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":"2607.17979","title":"Harness Engineering for LLM-Driven GPU Kernel Generation","created":"2026-07-20","cited_by_count":2,"area":null},{"id":"2607.19321","title":"ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2607.20466","title":"JAXBench: Benchmarking Autonomous TPU Kernel Optimization","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2607.25090","title":"Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering","created":"2026-07-27","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":"2511.22651","title":"Automated Design Optimization via Strategic Search with Large Language Models","created":"2025-11-27","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":"2602.09051","title":"RuleFlow : Generating Reusable Program Optimizations with LLMs","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2602.12049","title":"Improving HPC Code Generation Capability of LLMs via Online Reinforcement Learning with Real-Machine Benchmark Rewards","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2602.21143","title":"A Benchmark for Deep Information Synthesis","created":"2026-02-24","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":"2605.09708","title":"Metal-Sci: A Scientific Compute Benchmark for Evolutionary LLM Kernel Search on Apple Silicon","created":"2026-05-10","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":"2606.09956","title":"Multi-task LLMs for Bug Classification: Efficient Inference with Auxiliary Decoding Heads","created":"2026-06-08","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":"2607.16228","title":"Operator-Aware Mixed-Precision Tolerance Calibration for Tensor Kernels","created":"2026-06-23","cited_by_count":1,"area":null},{"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":"2609.10226","title":"$\\Phi$-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2510.24035","title":"GraphNet: A Large-Scale Computational Graph Dataset for Tensor Compiler Research","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2602.10387","title":"Test-Time Optimization of Physical Query Plans with LLMs","created":"2026-02-11","cited_by_count":0,"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":"2603.14501","title":"CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language","created":"2026-03-15","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":"2605.17978","title":"AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code","created":"2026-05-18","cited_by_count":0,"area":null},{"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":"2606.02963","title":"KForge: LLM-Driven Cross-Platform Kernel Generation for AI Accelerators","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.04023","title":"CodegenBench: Can LLMs Write Efficient Code Across Architectures?","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.09686","title":"Golden Ruler: A Numeric Format Catalog with Bit-Exact Conformance Vectors for FP8, BF16, MXFP4, and Microscaling Formats","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.26383","title":"SOLAR: AI-Powered Speed-of-Light Performance Analysis","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.27396","title":"Test-Input Generation for Tensor Programs: What Actually Finds Kernel Bugs","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.30442","title":"The FIL Hypothesis: Inductive Biases Help with Kernel Engineering","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.18357","title":"Decode-Time Grammars: Constrained LLM Generation over a Refinement Order of Grammar Fragments","created":"2026-07-20","cited_by_count":0,"area":null},{"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":"2607.24647","title":"Efficiency Matters in Autonomous Research","created":"2026-07-27","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":"2608.03983","title":"Can Large Language Models Recover Semantic Optimization Opportunities That Compilers Miss?","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.05033","title":"SparseDitto: An Agentic Sparse Compilation Framework through Architecture-Aware Synthesis on GPUs","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.10795","title":"EvoMem: Memory-Augmented Evolution for Code Optimization","created":"2026-08-11","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}],"next_cursor":"100"}