让大模型系统性探索多种解法，显著提升推理多样性与准确率。
Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options
- 通过压缩可解释的任务表示，强制模型生成多样化解法
- 在数据科学任务上提升38.2%至69.2%，在药物化学任务上提升37.4%至47.9%
- 成本低于1美元/任务，适合高成本敏感场景
我们提出一种名为Flow-of-Options（FoO）的新推理方法，旨在解决大语言模型（LLMs）固有的认知偏差。该方法通过压缩且可解释的任务表示，促使模型在推理过程中系统性地探索多样化的解决方案。基于FoO的智能体框架被用于自主解决机器学习任务，相较当前最优基线，在标准数据科学任务上性能提升38.2%–69.2%，在治疗化学任务上提升37.4%–47.9%。整体操作成本低于1美元/任务，适用于成本敏感型应用。此外，我们的实验表明，该方法不仅适用于表格分类与回归，还可扩展至强化学习和图像生成等更广泛任务。代码已开源：https://github.com/flagshippioneering/Flow-of-Options。
原文摘要 · Abstract (English)
We present a novel reasoning approach called Flow-of-Options (FoO), designed to address intrinsic biases in Large Language Models (LLMs). Flow-of-Options enables LLMs to systematically explore a diverse range of possibilities in their reasoning, as demonstrated by an FoO-based agentic framework developed for autonomously solving Machine Learning (ML) tasks. FoO enforces diversity in LLM solutions through compressed and interpretable task representations, resulting in improvements of 38.2% - 69.2% on standard data science tasks, and 37.4% - 47.9% on therapeutic chemistry tasks, as compared to state-of-the-art baselines. With an overall operation cost under $1 per task, our framework is well-suited for cost-sensitive applications. Going beyond tabular classification and regression, we show the broader applicability of our FoO-based agentic system to tasks such as reinforcement learning and image generation. Our code is open-sourced at: https://github.com/flagshippioneering/Flow-of-Options.
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。