2 papers
cs.CL2025
Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning
Xuetao Ma, Wenbin Jiang, Hua Huang
In-context learning (ICL) can significantly enhance the complex reasoning capabilities of large language models (LLMs), with the key lying in the selection and ordering of demonstr…
cs.SE2025
Process-Supervised Reinforcement Learning for Code Generation
Yufan Ye, Ting Zhang, Wenbin Jiang +1
Existing reinforcement learning strategies based on outcome supervision have proven effective in enhancing the performance of large language models(LLMs) for code generation. While…