# Diffusion Forcing for Multi-Agent Interaction Sequence Modeling

arXiv: https://arxiv.org/abs/2512.17900 · HTML: https://mlsanity.com/paper/2512.17900/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 35 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Builds on (most cited first, 30 of 32)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis](https://mlsanity.com/paper/2212.04495/) (2022)
- [InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions](https://mlsanity.com/paper/2304.05684/) (2023)
- [A Spatio-temporal Transformer for 3D Human Motion Prediction](https://mlsanity.com/paper/2004.08692/) (2020)
- [Inter-X: Towards Versatile Human-Human Interaction Analysis](https://mlsanity.com/paper/2312.16051/) (2023)
- [Multi-Person Extreme Motion Prediction](https://mlsanity.com/paper/2105.08825/) (2021)
- [ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions](https://mlsanity.com/paper/2311.17057/) (2023)
- [Estimating Body and Hand Motion in an Ego-sensed World](https://mlsanity.com/paper/2410.03665/) (2024)
- [Interactive Character Control with Auto-Regressive Motion Diffusion Models](https://mlsanity.com/paper/2306.00416/) (2023)
- [ReGenNet: Towards Human Action-Reaction Synthesis](https://mlsanity.com/paper/2403.11882/) (2024)
- [TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis](https://mlsanity.com/paper/2307.15042/) (2023)
- [Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment](https://mlsanity.com/paper/2403.18811/) (2024)
- [Generative Proxemics: A Prior for 3D Social Interaction from Images](https://mlsanity.com/paper/2306.09337/) (2023)
- [Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation](https://mlsanity.com/paper/2502.20370/) (2025)
- [DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling](https://mlsanity.com/paper/2506.18680/) (2025)
- [Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis](https://mlsanity.com/paper/2508.02106/) (2025)
- [Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset](https://mlsanity.com/paper/2510.16258/) (2025)
- [Synergy and Synchrony in Couple Dances](https://mlsanity.com/paper/2409.04440/) (2024)
- [Vision-based Multi-future Trajectory Prediction: A Survey](https://mlsanity.com/paper/2302.10463/) (2023)
- [ARFlow: Human Action-Reaction Flow Matching with Physical Guidance](https://mlsanity.com/paper/2503.16973/) (2025)

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

- [EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcing](https://mlsanity.com/paper/2605.13041/) (2026)
- [InterSing: Explicit Interaction Dynamics for 3D Duet Singing Animation and Beyond](https://mlsanity.com/paper/2609.04903/) (2026)
- [Generative Interactions: Weaving Multiparty Human Motion with Bilevel Latent Dynamics](https://mlsanity.com/paper/2609.37708/) (2026)
- [World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories](https://mlsanity.com/paper/2610.01742/) (2026)

## Abstract (arXiv)

Understanding and generating multi-person interactions is a fundamental challenge with broad implications for robotics and social computing. While humans naturally coordinate in groups, modeling such interactions remains difficult due to long temporal horizons, strong inter-agent dependencies, and variable group sizes. Existing motion generation methods are largely task-specific and do not generalize to flexible multi-agent generation. We introduce MAGNet (Multi-Agent Generative Network), a unified autoregressive diffusion framework for multi-agent motion generation that supports a wide range of interaction tasks through flexible conditioning and sampling. MAGNet performs dyadic and polyadic prediction, partner inpainting, partner prediction, and agentic generation all within a single model, and can autoregressively generate ultra-long sequences spanning hundreds of motion steps. We explicitly model inter-agent coupling during autoregressive denoising, enabling coherent coordination across agents. As a result, MAGNet captures both tightly synchronized activities (e.g., dancing, boxing) and loosely structured social interactions. Our approach performs on par with specialized methods on dyadic benchmarks while naturally extending to polyadic scenarios involving three or more interacting people. Please watch the supplemental video, where the temporal dynamics and spatial coordination of generated interactions are best appreciated. Project page: https://von31.github.io/MAGNet/