KernelClaw: A Multi-Agent Framework for GPU Kernel Optimization with Dual-Memory Mechanisms

arXiv:2603.10085 · cs.LG, cs.AI, cs.MA · Submitted 2026-03-10 · Read on arXiv

cs.LG, cs.AI, cs.MA

Submitted: 2026-03-10

Updated: 2026-10-18

Terminology

• Multi-Agent Framework — 2× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 8 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks