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

Lakshmi Nair, Ian Trase, Mark Kim
2/18/2025
cs.LGcs.AIcs.CL

Official code: flagshippioneering/Flow-of-Options (9 stars, last commit 2025-08-08).

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.

View on arXivView PDF

Code Implementations(1)

flagshippioneering/Flow-of-OptionsOfficial100%

[ICML'25] Flow-of-Options (FoO) - an inference time strategy to overcome intrinsic biases of LLMs

92PythonFeb 14, 20251 years agoNOASSERTION

Similar Papers

Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples

88% match1 repo1282024

Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples

88% match1 repo1282026

A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems

86% match2025

FlowRL: Matching Reward Distributions for LLM Reasoning

85% match2025

Rectifying LLM Thought from Lens of Optimization

85% match1 repo152025

Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought

85% match2024

Cite this paper

@article{nair2025flowofoptions,
  title  = {Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options},
  author = {Lakshmi Nair and Ian Trase and Mark Kim},
  year   = {2025},
  eprint = {2502.12929},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.12929v2},
  journal = {ICML 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.12929.svg)](https://codeofpaper.com/paper/2502.12929)

Discussion