SKILL: Self-correcting Knowledge-guided Iterative Large Language Model Agent for Logic Optimization: Logic synthesis optimization...
Poses significant challenges due to exponentially growing search spaces, sparse reward signals, and diverse logic structures. Traditional expert-designed flows lack adaptability, while reinforcement learning (RL) methods often suffer from low sample efficiency and limited interpretability. We introduce SKILL, a Self-correcting...
Source Brief
SKILL: Self-correcting Knowledge-guided Iterative Large Language Model Agent for Logic Optimization: Logic synthesis optimization poses significant challenges due to exponentially growing search spaces, sparse reward signals, and diverse logic structures. Traditional expert-designed flows lack adaptability, while reinforcement learning (RL) methods often suffer from low sample efficiency and limited interpretability. We introduce SKILL, a Self-correcting...