3 papers
cs.LG2026
Beyond Scaling: Self-Evolving LLM Agents for Hardware Kernel Optimization via an Experience-Driven Workflow and Experience Graph Memory
Siyuan Chen, Runlin Hou, Shenxiu Wu +7
Hardware kernel optimization requires repeated compilation, correctness testing, profiling, and revision. LLM agents can automate parts of this process, and stronger foundation mod…
cs.AI2026
AgenticCANN: Automated Ascend C Operator Generation via Knowledge-Augmented Agentic Evolution
Junhao Qiu, Zidong Wang, Yansong Sun +3
Ascend C operator optimization is critical for NPU (Neural Processing Unit) inference performance but requires deep hardware expertise. While large language models (LLMs) have show…
cs.SE2026
Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Hardware Operators
Yansong Sun, Shenxiu Wu, Siyuan Chen +6
Kernel generation for hardware accelerators such as GPUs and NPUs has become a proving ground for large language models (LLMs), and state-of-the-art systems raise correctness throu…