mlsanityData to 7 Oct 2026

Learning Shortest Paths with Generative Flow Networks

arXiv 2603.01786 ↗First posted 2 Mar 2026cs.LG cs.AI stat.MLcited by 2

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a novel learning framework for finding shortest paths in graphs utilizing Generative Flow Networks (GFlowNets). First, we examine theoretical properties of GFlowNets in non-acyclic environments in relation to shortest paths. We prove that, if the total flow is minimized, forward and backward policies traverse the environment graph exclusively along shortest paths between the initial and terminal states. Building on this result, we show that the pathfinding problem in an arbitrary graph can be solved by training a non-acyclic GFlowNet with flow regularization. We experimentally demonstrate the performance of our method in pathfinding in permutation environments and in solving Rubik's Cubes. For the latter problem, our approach shows competitive results with state-of-the-art machine learning approaches designed specifically for this task in terms of the solution length, while requiring smaller search budget at test-time.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 29 of its 49 references that are in the map. First posted on arXiv 2 Mar 2026.

Builds on

29 of 49 references.

References · 29

  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  2. 2016Layer Normalizationcited by 5,579
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  4. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  5. 2021GFlowNet Foundationscited by 286
  6. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 244
  7. 2022Bayesian Structure Learning with Generative Flow Networkscited by 153
  8. 2022Learning GFlowNets from partial episodes for improved convergence and stabilitycited by 129
  9. 2020If beam search is the answer, what was the question?cited by 114
  10. 2022GFlowNets and variational inferencecited by 103
  11. 2023Amortizing intractable inference in large language modelscited by 94
  12. 2023Generative Flow Networks as Entropy-Regularized RLcited by 60
17 more
  1. 2024Ant Colony Sampling with GFlowNets for Combinatorial Optimizationcited by 53
  2. 2023Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Networkcited by 50
  3. 2024Discrete Probabilistic Inference as Control in Multi-path Environmentscited by 40
  4. 2022A Variational Perspective on Generative Flow Networkscited by 39
  5. 2024RGFN: Synthesizable Molecular Generation Using GFlowNetscited by 39
  6. 2023DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNetscited by 27
  7. 2024SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraintscited by 26
  8. 2018Solving the Rubik's Cube Without Human Knowledgecited by 15
  9. 2024Pessimistic Backward Policy for GFlowNetscited by 13
  10. 2023A Theory of Non-Acyclic Generative Flow Networkscited by 12
  11. 2024Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximizationcited by 12
  12. 2017A Survey of Shortest-Path Algorithmscited by 10
  13. 2024Improving GFlowNets with Monte Carlo Tree Searchcited by 8
  14. 2025Revisiting Non-Acyclic GFlowNets in Discrete Environmentscited by 8
  15. 2025CayleyPy RL: Pathfinding and Reinforcement Learning on Cayley Graphscited by 5
  16. 2021Self-Supervision is All You Need for Solving Rubik's Cubecited by 4
  17. 2025gfnx: Fast and Scalable Library for Generative Flow Networks in JAXcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Your GFlowNet Secretly Learns an Optimal Transport Plancited by 0
  2. 2026Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernelscited by 0