Empirical evaluation finds reasoning LLMs improve code correction across iterations using execution feedback and outperform non-reasoning models, with syntactic and runtime errors easier to fix than logical ones.
GPU Kernel Scientist: An LLM-driven framework for iterative kernel optimization
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
KLineage derives verified optimization skills from backward lineages of expert GPU kernels to guide LLM agents toward higher-quality and more efficient kernels than memory-based baselines.
Optimas deploys a multi-agent LLM workflow to convert performance diagnostics into correct code transformations, delivering 100% valid code and performance gains in 98.82% of 3,410 experiments across benchmarks and HPC applications.
Glia deploys a multi-agent LLM workflow with reasoning, experimentation, and analysis agents to generate interpretable algorithms for request routing, scheduling, and auto-scaling in distributed GPU clusters, reaching human-expert performance levels.
AscendOptimizer combines kernel rewinding for reusable experience with evolutionary search on hardware feedback to optimize Ascend NPU operators, delivering 1.21x geometric-mean speedup and faster performance on 53.47% of 101 tested operators versus baseline.
citing papers explorer
-
Glia: A Human-Inspired AI for Automated Systems Design and Optimization
Glia deploys a multi-agent LLM workflow with reasoning, experimentation, and analysis agents to generate interpretable algorithms for request routing, scheduling, and auto-scaling in distributed GPU clusters, reaching human-expert performance levels.