# GFlowState: Visualizing the Training of Generative Flow Networks Beyond the Reward

arXiv: https://arxiv.org/abs/2604.21830 · HTML: https://mlsanity.com/paper/2604.21830/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation](https://mlsanity.com/paper/2106.04399/) (2021)
- [GFlowNet Foundations](https://mlsanity.com/paper/2111.09266/) (2021)
- [Tackling Climate Change with Machine Learning](https://mlsanity.com/paper/1906.05433/) (2019)
- [Trajectory balance: Improved credit assignment in GFlowNets](https://mlsanity.com/paper/2201.13259/) (2022)
- [The Open Catalyst 2020 (OC20) Dataset and Community Challenges](https://mlsanity.com/paper/2010.09990/) (2020)
- [Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers](https://mlsanity.com/paper/1801.06889/) (2018)
- [Towards Understanding and Improving GFlowNet Training](https://mlsanity.com/paper/2305.07170/) (2023)
- [Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models](https://mlsanity.com/paper/1804.09299/) (2018)
- [Graying the black box: Understanding DQNs](https://mlsanity.com/paper/1602.02658/) (2016)
- [GFlowNets for AI-Driven Scientific Discovery](https://mlsanity.com/paper/2302.00615/) (2023)
- [CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization](https://mlsanity.com/paper/2004.15004/) (2020)
- [A Survey of Visual Analytics Techniques for Machine Learning](https://mlsanity.com/paper/2008.09632/) (2020)
- [GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation](https://mlsanity.com/paper/1809.01587/) (2018)
- [Why? Why not? When? Visual Explanations of Agent Behavior in Reinforcement Learning](https://mlsanity.com/paper/2104.02818/) (2021)
- [ConfusionFlow: A model-agnostic visualization for temporal analysis of classifier confusion](https://mlsanity.com/paper/1910.00969/) (2019)
- [Visual Comparison of Language Model Adaptation](https://mlsanity.com/paper/2208.08176/) (2022)
- [Revealing the Unwritten: Visual Investigation of Beam Search Trees to Address Language Model Prompting Challenges](https://mlsanity.com/paper/2310.11252/) (2023)
- [InstanceFlow: Visualizing the Evolution of Classifier Confusion on the Instance Level](https://mlsanity.com/paper/2007.11353/) (2020)
- [generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation](https://mlsanity.com/paper/2403.07627/) (2024)
- [Juniper: A Tree+Table Approach to Multivariate Graph Visualization](https://mlsanity.com/paper/1804.03261/) (2018)
- [EvolvED: Evolutionary Embeddings to Understand the Generation Process of Diffusion Models](https://mlsanity.com/paper/2406.17462/) (2024)
- [Catalyst GFlowNet for electrocatalyst design: A hydrogen evolution reaction case study](https://mlsanity.com/paper/2510.02142/) (2025)

## Abstract (arXiv)

We present GFlowState, a visual analytics system designed to illuminate the training process of Generative Flow Networks (GFlowNets or GFNs). GFlowNets are a probabilistic framework for generating samples proportionally to a reward function. While GFlowNets have proved to be powerful tools in applications such as molecule and material discovery, their training dynamics remain difficult to interpret. Standard machine learning tools allow metric tracking but do not reveal how models explore the sample space, construct sample trajectories, or shift sampling probabilities during training. Our solution, GFlowState, allows users to analyze sampling trajectories, compare the sample space relative to reference datasets, and analyze the training dynamics. To this end, we introduce multiple views, including a chart of candidate rankings, a state projection, a node-link diagram of the trajectory network, and a transition heatmap. These visualizations enable GFlowNet developers and users to investigate sampling behavior and policy evolution, and to identify underexplored regions and sources of training failure. Case studies demonstrate how the system supports debugging and assessing the quality of GFlowNets across application domains. By making the structural dynamics of GFlowNets observable, our work enhances their interpretability and can accelerate GFlowNet development in practice.