mlsanityData to 7 Oct 2026

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

arXiv 2502.12929 ↗First posted 18 Feb 2025cs.LG cs.AI cs.CLcited by 3

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 13 of its 47 references that are in the map. First posted on arXiv 18 Feb 2025.

Builds on

13 of 47 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning22 Dec

Other references · 12

  1. 2024GPT-4o System Cardcited by 4,467
  2. 2016OpenAI Gymcited by 1,684
  3. 2024A Survey on LLM-as-a-Judgecited by 1,384
  4. 2020AutoGluon-Tabular: Robust and Accurate AutoML for Structured Datacited by 368
  5. 2024Data Interpreter: An LLM Agent For Data Sciencecited by 222
  6. 2018Marian: Fast Neural Machine Translation in C++cited by 202
  7. 2024ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Modelscited by 200
  8. 2024Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agentscited by 94
  9. 2022Democratizing Neural Machine Translation with OPUS-MTcited by 57
  10. 2024DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaborationcited by 40
  11. 2024SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learningcited by 23
  12. 2024Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performancecited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Large Language Models for Planning: A Comprehensive and Systematic Surveycited by 38
  2. 2025A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Lawcited by 18
  3. 2026Diverse Thinking Schemata Elicit Better Reasoning in Large Language Modelscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
  2. 2025FlowRL: Matching Reward Distributions for LLM Reasoning
  3. 2025Agent-as-Tool: A Study on the Hierarchical Decision Making with Reinforcement Learning
  4. 2024Designing Algorithms Empowered by Language Models: An Analytical Framework, Case Studies, and Insights
  5. 2025Revisiting LLM Reasoning via Information Bottleneck
  6. 2025OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLM
  7. 2026FlowEdit: Information-Theoretic Control of LLM Reasoning Flows for Ill-posed Problems Involving Conflicts
  8. 2024Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning