Location: Singapore Expo (Room TBD)

What This Workshop Is About

The Multi-Agent Path Finding (MAPF) problem is at the heart of a wide range of deployed systems, including warehouse automation, autonomous aircraft towing, service robots, and video game crowd simulation. MAPF asks to compute collision-free trajectories that move a set of agents (e.g., robotic manipulators and warehouse robots) from specified start to goal configurations while optimising a global objective, typically the sum of travel costs or the makespan. For many such objectives the problem is NP-hard, and even achieving meaningful approximation guarantees is intractable, making high-quality real-time planning a persistent challenge. This workshop aims to bring these researchers together to present their research, discuss future research directions, and cross-fertilize the different communities.

Important Dates

Date	Event
22/10/2025 (AOE)	Paper Submission Deadline
05/11/2025	Notifications Sent to Authors
16/11/2025 (11:59 Eastern Time)	AAAI-26 Early Registration Deadline
26/01/2026	Workshop Date

Call for Contributions

We invite high-quality paper submissions focusing on Multi-Agent Path Finding (MAPF). Selected papers will be invited to be presented in a lightning talk or poster session during the workshop, and a best paper award will be chosen among the participants. Topics of interest include, but are not limited to:

• Search-, rule-, reduction-, reactive-, and learning-based planners
• Planning and execution algorithms for dynamic or uncertain environments
• Decentralised MAPF and multi-agent reinforcement learning
• Kinodynamically feasible multi-agent planning
• Planning in continuous time and space
• Customised MAPF planners for real robots
• Cooperation in heterogeneous robot teams
• Surveys of MAPF modeling, solvers, or benchmarks
• Multi-robot or human-multi-robot collaboration
• Multi-agent LLM systems with MAPF methods
• Live demo of relevant software or hardware systems

There is no required format for the submissions. If possible, we recommend the AAAI 2026 style. The workshop is non-archival.

We encourage interested participants to submit ongoing research as well as recent publications. Submissions will be reviewed by a Program Committee assembled from the organizers, the advisory board, and other experts in the field.

Accepted papers will be made available on the workshop website and the authors will be invited to present their work as a short talk during the workshop and/or as a poster.

Contact Us

For any questions or inquiries, please email andy.li@monash.edu