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

TL;DR

Flow-of-Options (FoO) is a novel reasoning method for LLMs that promotes diversity in solutions, significantly improving performance on various tasks while maintaining low operational costs.

Contribution

The paper introduces Flow-of-Options, a new approach that systematically explores diverse reasoning paths in LLMs, enhancing accuracy and applicability across multiple domains.

Findings

Achieved 38.2%-69.2% improvement on data science tasks

Achieved 37.4%-47.9% improvement on therapeutic chemistry tasks

Demonstrated applicability to reinforcement learning and image generation

Abstract

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.