Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis
Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis explores EvoKernel automates kernel synthesis for data-scarce programming domains using a self-evolving agentic framework.. Commercial viability score: 8/10 in Kernel Synthesis.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $9K - $13K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Builds On ThisKernelFoundry: Hardware-aware evolutionary GPU kernel optimizationViability: 7.0
- Builds On ThisKernelBlaster: Continual Cross-Task CUDA Optimization via Memory-Augmented In-Context Reinforcement LearningViability: 7.0
- Builds On ThisCUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel GenerationViability: 3.0
- Builds On ThisMobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?Viability: 7.0
- Builds On ThisCuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe