How to Select Pre-Trained Code Models for Reuse? A Learning Perspective
Pre-training a language model and then fine-tuning it has shown to be an efficient and
effective technique for a wide range of code intelligence tasks, such as code generation …
effective technique for a wide range of code intelligence tasks, such as code generation …
Process-Supervised Reinforcement Learning for Code Generation
Y Ye, T Zhang, W Jiang, H Huang - arxiv preprint arxiv:2502.01715, 2025 - arxiv.org
Existing reinforcement learning strategies based on outcome supervision have proven
effective in enhancing the performance of large language models (LLMs) for code …
effective in enhancing the performance of large language models (LLMs) for code …
PATCH: Empowering Large Language Model with Programmer-Intent Guidance and Collaborative-Behavior Simulation for Automatic Bug Fixing
Bug fixing holds significant importance in software development and maintenance. Recent
research has made substantial strides in exploring the potential of large language models …
research has made substantial strides in exploring the potential of large language models …