# From Discrete Plans to Real-World Execution: A World-Model-Driven Framework for Execution-Aware Multi-Agent Path Finding

arXiv: https://arxiv.org/abs/2511.21886 · HTML: https://mlsanity.com/paper/2511.21886/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 26 Nov 2025.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Multi-Agent Pathfinding: Definitions, Variants, and Benchmarks](https://mlsanity.com/paper/1906.08291/) (2019)
- [ETA Prediction with Graph Neural Networks in Google Maps](https://mlsanity.com/paper/2108.11482/) (2021)
- [Searching with Consistent Prioritization for Multi-Agent Path Finding](https://mlsanity.com/paper/1812.06356/) (2018)
- [EECBS: A Bounded-Suboptimal Search for Multi-Agent Path Finding](https://mlsanity.com/paper/2010.01367/) (2020)
- [Conflict-based Search for Multi-Robot Motion Planning with Kinodynamic Constraints](https://mlsanity.com/paper/2207.00576/) (2022)
- [Scaling Lifelong Multi-Agent Path Finding to More Realistic Settings: Research Challenges and Opportunities](https://mlsanity.com/paper/2404.16162/) (2024)
- [Multi-Agent Motion Planning For Differential Drive Robots Through Stationary State Search](https://mlsanity.com/paper/2412.13359/) (2024)
- [Multi-Agent Motion Planning with B'ezier Curve Optimization under Kinodynamic Constraints](https://mlsanity.com/paper/2311.14145/) (2023)
- [Bidirectional Temporal Plan Graph: Enabling Switchable Passing Orders for More Efficient Multi-Agent Path Finding Plan Execution](https://mlsanity.com/paper/2401.00315/) (2023)
- [Speedup Techniques for Switchable Temporal Plan Graph Optimization](https://mlsanity.com/paper/2412.15908/) (2024)
- [Time-Independent Planning for Multiple Moving Agents](https://mlsanity.com/paper/2005.13187/) (2020)
- [Receding Horizon Re-ordering of Multi-Agent Execution Schedules](https://mlsanity.com/paper/2312.04190/) (2023)
- [Advancing MAPF Toward the Real World: A Scalable Multi-Agent Realistic Testbed (SMART)](https://mlsanity.com/paper/2503.04798/) (2025)
- [Graph Attention-Guided Search for Dense Multi-Agent Pathfinding](https://mlsanity.com/paper/2510.17382/) (2025)
- [A Real-Time Rescheduling Algorithm for Multi-robot Plan Execution](https://mlsanity.com/paper/2403.18145/) (2024)
- [Provably Safe and Deadlock-Free Execution of Multi-Robot Plans under Delaying Disturbances](https://mlsanity.com/paper/1603.08582/) (2016)
- [Reliable and Efficient Multi-Agent Coordination via Graph Neural Network Variational Autoencoders](https://mlsanity.com/paper/2503.02954/) (2025)
- [Online Re-Planning and Adaptive Parameter Update for Multi-Agent Path Finding with Stochastic Travel Times](https://mlsanity.com/paper/2302.01489/) (2023)
- [WinkTPG: An Execution Framework for Multi-Agent Path Finding Using Temporal Reasoning](https://mlsanity.com/paper/2508.01495/) (2025)

## Abstract (arXiv)

Multi-Agent Path Finding (MAPF) studies how to coordinate multiple agents to reach their goals without collisions and underpins a range of large-scale robotic systems, including automated warehousing and manufacturing. Recent advances enable MAPF solvers to compute high-quality plans for hundreds of agents. However, these plans are generated using simplified robot models with discretized time and action spaces. When they are deployed in physical systems, heterogeneous robot dynamics, asynchronous interactions, communication delays, and other real-world factors can lead to substantial deviations from planned performance. We bridge the gap between discrete planning and real-world execution through ExecTimeNet, a learned world model of MAPF execution that predicts how a discrete MAPF solution will unfold on physical robots, mapping each discrete action to its realized execution state, including its wall-clock completion time and the kinodynamic state in which it ends. Building on this capability, we first propose REMAP, an execution-aware MAPF framework that integrates execution-time estimation into planning, guiding the search toward MAPF solutions with improved execution performance. We also introduce ESADG, a post-planning optimization procedure that optimizes the execution schedule of a given MAPF solution while preserving path feasibility. We evaluate proposed frameworks in high-fidelity simulation with up to 300 agents and on physical robots. In simulation, ExecTimeNet predicts the execution state accurately and transfers to unseen maps and agent counts. Across simulation benchmarks spanning diverse map topologies, REMAP reduces delays by up to 21% over baselines, while ESADG achieves up to 40% normalized improvement. On physical hardware, the full pipeline reduces total execution time by up to 15.3%, demonstrating effective transfer from simulation to real-world deployment.