通过多样化推理与验证，显著提升大模型解决高难度数学与逻辑题的能力。
Diverse Inference and Verification for Advanced Reasoning
- 融合多模型多方法进行测试时推理，结合自动验证与拒绝采样。
- IMO组合题准确率从33.3%提升至77.8%，HLE题从8%升至37%。
- 适合需要高精度推理的竞赛级任务，支持可复现研究。
如OpenAI o1、o3和DeepSeek R1等推理型大模型在数学与编码任务上取得显著进展，但在国际数学奥林匹克（IMO）组合题、抽象推理语料库（ARC）谜题及人类最后考试（HLE）问题上仍面临挑战。本文提出一种测试时多样化推理方法，结合多个模型与策略。通过Lean自动验证IMO解法、用代码验证ARC谜题，最佳N选一策略有效解答HLE问题。该方法使IMO组合题准确率从33.3%提升至77.8%，HLE题准确率从8%增至37%，并解决80%人类无法解答的ARC谜题（948人未解），以及26.5% o3高算力未能解决的题目。测试时模拟、强化学习与基于推理反馈的元学习，通过调整代理图表示、提示词、代码与数据集，提升泛化能力。该方法可靠、鲁棒且可扩展，论文发表后将公开代码以支持可复现研究。
原文摘要 · Abstract (English)
Reasoning LLMs such as OpenAI o1, o3 and DeepSeek R1 have made significant progress in mathematics and coding, yet find challenging advanced tasks such as International Mathematical Olympiad (IMO) combinatorics problems, Abstraction and Reasoning Corpus (ARC) puzzles, and Humanity's Last Exam (HLE) questions. We use a diverse inference approach that combines multiple models and methods at test time. We find that verifying mathematics and code problems, and rejection sampling on other problems is simple and effective. We automatically verify correctness of solutions to IMO problems by Lean, and ARC puzzles by code, and find that best-of-N effectively answers HLE questions. Our approach increases answer accuracy on IMO combinatorics problems from 33.3% to 77.8%, accuracy on HLE questions from 8% to 37%, and solves 80% of ARC puzzles that 948 humans could not and 26.5% of ARC puzzles that o3 high compute does not. Test-time simulations, reinforcement learning, and meta-learning with inference feedback improve generalization by adapting agent graph representations and varying prompts, code, and datasets. Our approach is reliable, robust, and scalable, and in the spirit of reproducible research, we will make it publicly available upon publication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。