# Empowering Multi-Robot Cooperation via Sequential World Models

arXiv: https://arxiv.org/abs/2509.13095 · HTML: https://mlsanity.com/paper/2509.13095/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Latent dynamics models and model-based RL, one of 11 directions in World models.
- Builds on 8 of its 50 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Placed in

- World models / [Latent dynamics models and model-based RL](https://mlsanity.com/wm/latent-dynamics-models-and-model-based-rl/)
- Deep reinforcement learning methods / [RL for games and combinatorial optimization](https://mlsanity.com/deeprl/rl-for-games-and-combinatorial-optimization/)

## Builds on (most cited first, 8 of 8)

- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [DayDreamer: World Models for Physical Robot Learning](https://mlsanity.com/paper/2206.14176/) (2022)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [RoboDreamer: Learning Compositional World Models for Robot Imagination](https://mlsanity.com/paper/2404.12377/) (2024)
- [MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulation](https://mlsanity.com/paper/2309.14236/) (2023)
- [Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models](https://mlsanity.com/paper/2406.15836/) (2024)
- [Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective](https://mlsanity.com/paper/2505.20922/) (2025)
- [CoDreamer: Communication-Based Decentralised World Models](https://mlsanity.com/paper/2406.13600/) (2024)

## Built on by (most cited first, 9 of 9)

- [World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation](https://mlsanity.com/paper/2509.19080/) (2025)
- [CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic](https://mlsanity.com/paper/2511.12159/) (2025)
- [MultiWorld: Scalable Multi-Agent Multi-View Video World Models](https://mlsanity.com/paper/2604.18564/) (2026)
- [Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations](https://mlsanity.com/paper/2512.21586/) (2025)
- [Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models](https://mlsanity.com/paper/2605.18431/) (2026)
- [Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games](https://mlsanity.com/paper/2511.00811/) (2025)
- [RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning](https://mlsanity.com/paper/2510.14828/) (2025)
- [R2PS: Worst-Case Robust Real-Time Pursuit Strategies under Partial Observability](https://mlsanity.com/paper/2511.17367/) (2025)
- [CyberWorld: World Models for Sample-Efficient Autonomous Cyber Defense](https://mlsanity.com/paper/2609.31893/) (2026)

## Abstract (arXiv)

Model-based reinforcement learning (MBRL) has achieved remarkable success in robotics due to its high sample efficiency and planning capability. However, extending MBRL to physical multi-robot cooperation remains challenging due to the complexity of joint dynamics. To address this challenge, we propose the Sequential World Model (SeqWM), a novel framework that integrates the sequential paradigm into multi-robot MBRL. SeqWM employs independent, autoregressive agent-wise world models to represent joint dynamics, where each agent generates its future trajectory and plans its actions based on the predictions of its predecessors. This design lowers modeling complexity and enables the emergence of advanced cooperative behaviors through explicit intention sharing. Experiments on Bi-DexHands and Multi-Quadruped demonstrate that SeqWM outperforms existing state-of-the-art model-based and model-free baselines in both overall performance and sample efficiency, while exhibiting advanced cooperative behaviors such as predictive adaptation, temporal alignment, and role division. Furthermore, SeqWM has been successfully deployed on physical quadruped robots, validating its effectiveness in real-world multi-robot systems. Demos and code are available at: https://github.com/zhaozijie2022/seqwm