選項流：通過多樣化思考提升大型語言模型推理能力

Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options

February 18, 2025

作者: Lakshmi Nair, Ian Trase, Mark Kim

cs.AI

摘要

我們提出了一種名為「選項流」（Flow-of-Options, FoO）的新穎推理方法，旨在解決大型語言模型（LLMs）中的內在偏見。FoO使LLMs能夠在推理過程中系統性地探索多樣化的可能性，這一點通過一個基於FoO的自主解決機器學習任務（AutoML）的代理系統得到了展示。我們的框架在標準數據科學任務上超越了現有的最先進基準，取得了38.2%至69.2%的提升，在治療化學任務上則提升了37.4%至47.9%。每項任務的總操作成本低於1美元，使得我們的框架非常適合成本敏感的應用場景。除了分類和回歸，我們還展示了基於FoO的代理系統在強化學習和圖像生成等任務中的廣泛適用性。與當前最先進的AutoML代理系統相比，我們的框架展現了顯著的進步，這得益於FoO在通過壓縮且可解釋的表示來強制LLM解決方案多樣性方面的優勢，這些表示在與基於案例的推理結合時還支持長期記憶。

English

We present a novel reasoning approach called Flow-of-Options (FoO), designed to address intrinsic biases in Large Language Models (LLMs). FoO enables LLMs to systematically explore a diverse range of possibilities in their reasoning, as demonstrated by an FoO-based agentic system for autonomously solving Machine Learning tasks (AutoML). Our framework outperforms state-of-the-art baselines, achieving improvements of 38.2% - 69.2% on standard data science tasks, and 37.4% - 47.9% on therapeutic chemistry tasks. With an overall operation cost under $1 per task, our framework is well-suited for cost-sensitive applications. Beyond classification and regression, we illustrate the broader applicability of our FoO-based agentic system to tasks such as reinforcement learning and image generation. Our framework presents significant advancements compared to current state-of-the-art agentic systems for AutoML, due to the benefits of FoO in enforcing diversity in LLM solutions through compressed, explainable representations that also support long-term memory when combined with case-based reasoning.