# Learning Ad Hoc Network Dynamics via Graph-Structured World Models

arXiv: https://arxiv.org/abs/2604.14811 · HTML: https://mlsanity.com/paper/2604.14811/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 12 of 12)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Variational Graph Recurrent Neural Networks](https://mlsanity.com/paper/1908.09710/) (2019)
- [World Models for Cognitive Agents: Transforming Edge Intelligence in Future Networks](https://mlsanity.com/paper/2506.00417/) (2025)
- [Wireless Power Control via Counterfactual Optimization of Graph Neural Networks](https://mlsanity.com/paper/2002.07631/) (2020)
- [Relational State-Space Model for Stochastic Multi-Object Systems](https://mlsanity.com/paper/2001.04050/) (2020)
- [World Model-Based Learning for Long-Term Age of Information Minimization in Vehicular Networks](https://mlsanity.com/paper/2505.01712/) (2025)
- [Dual-Mind World Models: A General Framework for Learning in Dynamic Wireless Networks](https://mlsanity.com/paper/2510.24546/) (2025)

## Built on by (most cited first, 2 of 2)

- [Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies](https://mlsanity.com/paper/2609.28670/) (2026)
- [CyberWorld: World Models for Sample-Efficient Autonomous Cyber Defense](https://mlsanity.com/paper/2609.31893/) (2026)

## Abstract (arXiv)

Ad hoc wireless networks exhibit complex, innate and coupled dynamics: node mobility, energy depletion and topology change that are difficult to model analytically. Model-free deep reinforcement learning requires sustained online interaction whereas existing model based approaches use flat state representations that lose per node structure. Therefore we propose G-RSSM, a graph structured recurrent state space model that maintains per node latent states with cross node multi head attention to learn the dynamics jointly from offline trajectories. We apply the proposed method to the downstream task clustering where a cluster head selection policy trains entirely through imagined rollouts in the learned world model. Across 27 evaluation scenarios spanning MANET, VANET, FANET, WSN and tactical networks with N=30 to 1000 nodes, the learned policy maintains high connectivity with only trained for N=50. Herein, we propose the first multi physics graph structured world model applied to combinatorial per node decision making in size agnostic wireless ad hoc networks.