研究人员开发了新方法来提高大型语言模型生成正确代码和证明的能力。一种方法 TTRL-CoCoV 使用置信度条件验证来增强无标签设置下的覆盖率和准确性，在多个基准测试中显示出显著的提升。另一项研究探索使用强化学习和递归推理来自动化形式验证，通过将证明生成视为结构化搜索过程，实现了更高的验证程序生成率。 AI
影响 这些方法可以显著提高 AI 生成代码和形式证明的可靠性和正确性。
排序理由 两篇 arXiv 论文详细介绍了用于改进 LLM 代码生成和形式验证的新研究方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.03608v1 Announce Type: cross Abstract: Test-time reinforcement learning has emerged as a promising paradigm for enhancing the complex reasoning abilities of large language models in a completely label-free manner. Despite existing studies focusing on Pass@1 performance…
Test-time reinforcement learning has emerged as a promising paradigm for enhancing the complex reasoning abilities of large language models in a completely label-free manner. Despite existing studies focusing on Pass@1 performance, optimizing Pass@k remains under-explored yet cri…
arXiv:2605.30914v1 Announce Type: new Abstract: Automated formal verification remains challenging for large language models because data for proof assistants and verification-aware languages is scarce, and correctness depends on satisfying precise machine-checkable specifications…