7 papers
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…
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…
Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Accelerator Kernels
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…
A Sliding-Window-Based Reinforcement Learning for Dynamic Assembly Flow Shop Scheduling with Multi-Product Delivery
Junhao Qiu, Jianjun Liu, Ting Liu +3
Multi-product kitting delivery imposes significant challenges for real-time scheduling in hybrid manufacturing systems that integrate processing and assembly, as dynamic order arri…
Evolving Interdependent Operators with Large Language Models for Multi-Objective Combinatorial Optimization
Junhao Qiu, Xin Chen, Liang Ge +3
Neighborhood search operators are critical to the performance of Multi-Objective Evolutionary Algorithms (MOEAs) and rely heavily on expert design. Although recent LLM-based Automa…
EvoDR: Evolving Dispatching Rules via Large Language Model for Dynamic Flexible Assembly Flow Shop Scheduling
Junhao Qiu, Haoyang Zhuang, Fei Liu +2
Dynamic flexible assembly flow shop scheduling with multi-product delivery is a critical combinatorial problem, characterized by kitting supply and machine flexibility. Genetic pro…
Online Operator Design in Evolutionary Optimization for Flexible Job Shop Scheduling via Large Language Models
Rongjie Liao, Junhao Qiu, Xin Chen +1
Customized static operator design has enabled widespread application of Evolutionary Algorithms (EAs), but their search effectiveness often deteriorates as evolutionary progresses.…