Author name: Shan Jiang, Zijian Yi, Chenguang Zhu

arXiv:2605.08658v1 Announce Type: new
Abstract: SKETCHVERIFY is a within-tier cost-performance policy, not a universal accuracy improvement. The operational question: a practitioner stuck with a small, cheap code model (here, Gemini 3.1 Flash Lite) fo…

arXiv:2605.08680v1 Announce Type: cross
Abstract: LLM code-generation pipelines often sample multiple candidates and select one final answer without access to a complete oracle. Existing pipelines mix textual voting, ranking, and execution-based agree…