arXiv:2501.09891cs.AI2025-01被引 54

用进化算法提升大模型推理能力,无需手动设计逻辑。

Evolving Deeper LLM Thinking

  • 让大模型自动生成、重组并优化回答,动态演化思维过程。
  • 在旅行规划等任务中,98%以上问题能正确解决,超越传统方法。
  • 适合需要深度推理但无明确解法的复杂任务场景。

我们探索了一种用于扩展大型语言模型推理时间计算量的进化搜索策略。所提出的思路——心智演化(Mind Evolution),利用语言模型生成、重组并精炼候选回答。该方法在存在解决方案评估器时,无需形式化底层推理问题即可运行。在控制推理成本的前提下,我们发现心智演化在自然语言规划任务中显著优于其他推理策略,如Best-of-N和顺序修订。在TravelPlanner和Natural Plan基准测试中,仅使用Gemini 1.5 Pro模型,不依赖形式化求解器,便解决了超过98%的问题实例。

原文摘要 · Abstract (English)

We explore an evolutionary search strategy for scaling inference time compute in Large Language Models. The proposed approach, Mind Evolution, uses a language model to generate, recombine and refine candidate responses. The proposed approach avoids the need to formalize the underlying inference problem whenever a solution evaluator is available. Controlling for inference cost, we find that Mind Evolution significantly outperforms other inference strategies such as Best-of-N and Sequential Revision in natural language planning tasks. In the TravelPlanner and Natural Plan benchmarks, Mind Evolution solves more than 98% of the problem instances using Gemini 1.5 Pro without the use of a formal solver.

大模型推理进化算法自主思考

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。