Abstract: Code Large Language Models (CodeLLMs) have demonstrated impressive proficiency in code completion tasks. However, they often fall short of fully understanding the extensive context of a ...

Abstract: Q-learning and double Q-learning are well-known sample-based, off-policy reinforcement learning algorithms. However, Q-learning suffers from overestimation bias, while double Q-learning ...

CGBridge is a novel framework designed to enhance the code understanding capabilities of Large Language Models (LLMs) by integrating rich structural information from code graphs. Our approach follows ...