# Learning Individual Behavior in Agent-Based Models with Graph Diffusion Networks

arXiv: https://arxiv.org/abs/2505.21426 · HTML: https://mlsanity.com/paper/2505.21426/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 17 of its 51 references that are in the map.
- First posted on arXiv 27 May 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Equivariant Diffusion for Molecule Generation in 3D](https://mlsanity.com/paper/2203.17003/) (2022)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2205.15019/) (2022)
- [Generative Diffusion Models on Graphs: Methods and Applications](https://mlsanity.com/paper/2302.02591/) (2023)
- [Learning Graph Cellular Automata](https://mlsanity.com/paper/2110.14237/) (2021)
- [Automatic Differentiation of Programs with Discrete Randomness](https://mlsanity.com/paper/2210.08572/) (2022)
- [Conditional Image Synthesis with Diffusion Models: A Survey](https://mlsanity.com/paper/2409.19365/) (2024)
- [Learning Opinion Dynamics From Social Traces](https://mlsanity.com/paper/2006.01673/) (2020)
- [On learning agent-based models from data](https://mlsanity.com/paper/2205.05052/) (2022)
- [Learning stochastic dynamics and predicting emergent behavior using transformers](https://mlsanity.com/paper/2202.08708/) (2022)
- [Reinforcement Learning for Combining Search Methods in the Calibration of Economic ABMs](https://mlsanity.com/paper/2302.11835/) (2023)
- [Data assimilation with agent-based models using Markov chain sampling](https://mlsanity.com/paper/2205.01616/) (2022)

## Built on by (most cited first, 4 of 4)

- [Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physics](https://mlsanity.com/paper/2605.10528/) (2026)
- [Microscopic dynamics of consensus formation in multi-agent LLM Naming Games](https://mlsanity.com/paper/2608.02178/) (2026)
- [Comparing Data Assimilation and Likelihood-Based Inference on Latent State Estimation in Agent-Based Models](https://mlsanity.com/paper/2509.17625/) (2025)
- [A differentiable model of supply-chain shocks](https://mlsanity.com/paper/2511.05231/) (2025)

## Abstract (arXiv)

Agent-Based Models (ABMs) are powerful tools for studying emergent properties in complex systems. In ABMs, agent behaviors are governed by local interactions and stochastic rules. However, these rules are, in general, non-differentiable, limiting the use of gradient-based methods for optimization, and thus integration with real-world data. We propose a novel framework to learn a differentiable surrogate of any ABM by observing its generated data. Our method combines diffusion models to capture behavioral stochasticity and graph neural networks to model agent interactions. Distinct from prior surrogate approaches, our method introduces a fundamental shift: rather than approximating system-level outputs, it models individual agent behavior directly, preserving the decentralized, bottom-up dynamics that define ABMs. We validate our approach on two ABMs (Schelling's segregation model and a Predator-Prey ecosystem) showing that it replicates individual-level patterns and accurately forecasts emergent dynamics beyond training. Our results demonstrate the potential of combining diffusion models and graph learning for data-driven ABM simulation.