S*: Test Time Scaling for Code Generation

D Li, S Cao, C Cao, X Li, S Tan, K Keutzer… - arxiv preprint arxiv …, 2025 - arxiv.org
Increasing test-time compute for LLMs shows promise across domains but remains
underexplored in code generation, despite extensive study in math. In this paper, we …

Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation

K Du, H Wang, J Liu, J Chen, X Dai, Y Wang… - arxiv preprint arxiv …, 2025 - arxiv.org
Large language models (LLMs) have demonstrated remarkable capabilities in various
domains, particularly in system 1 tasks, yet the intricacies of their problem-solving …