两篇新研究论文探讨了在Lean环境中提高大型语言模型（LLM）在形式定理证明中的效率和有效性的方法。第一篇论文介绍了一种动作路由代理，该代理通过使用编译器反馈来指导搜索并降低计算成本，从而优化成本-质量权衡。第二篇论文提出了一种“反馈蒸馏”训练方法，该方法利用语言模型的反馈来改进令牌级别的监督和探索，在生成多样化且成功的证明轨迹方面优于传统的强化学习技术。 AI
影响 这些论文提出了使LLM在形式定理证明等复杂推理任务中更高效、更有效的新技术，有可能加速AI在数学和科学发现中的应用。
排序理由 两篇在arXiv上发表的学术论文，详细介绍了改进LLM在形式定理证明中性能的新颖方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.04883v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in workflows for generating formal proofs in Lean. These workflows often decompose problems into smaller lemmas, sample many proof attempts, and use compiler feedback to guide searc…
Large language models (LLMs) are increasingly used in workflows for generating formal proofs in Lean. These workflows often decompose problems into smaller lemmas, sample many proof attempts, and use compiler feedback to guide search. However, they can be prohibitively expensive,…
arXiv:2605.30861v1 Announce Type: new Abstract: Post-training for reasoning models typically combines supervised fine-tuning with reinforcement learning from verifiable rewards, most commonly with GRPO. However, this algorithm suffers from sparse rewards, limited exploration, and…