2 papers
cs.SE2025
CodeReasoner: Enhancing the Code Reasoning Ability with Reinforcement Learning
Lingxiao Tang, He Ye, Zhongxin Liu +2
Code reasoning is a fundamental capability for large language models (LLMs) in the code domain. It involves understanding and predicting a program's execution behavior, such as det…
cs.SE2023
A^3-CodGen: A Repository-Level Code Generation Framework for Code Reuse with Local-Aware, Global-Aware, and Third-Party-Library-Aware
Dianshu Liao, Shidong Pan, Xiaoyu Sun +5
LLM-based code generation tools are essential to help developers in the software development process. Existing tools often disconnect with the working context, i.e., the code repos…