Multi-Agent Path Finding
Also known as MAPF
Overview
Multi-agent path finding studies how to route agents to their goals without collisions, often minimizing travel cost or completion time; in lifelong settings, agents repeatedly receive new tasks. Classical methods include Conflict-Based Search and space-time search for high-quality or optimal plans, while prioritized planning, PIBT, and LaCAM trade some solution quality for scalability. Other approaches use learning, local communication, optimization, or hybrid methods that combine fast planning with conflict repair, and many now address task assignment, congestion, and execution on real robots. A central tension is balancing guarantees and realistic motion or disturbances against the speed and scale needed for dense fleets.
Latest papers
100 papers13 papers in the last four weeks, up 44% on the four weeks before. 0.1% of all new papers.
Travel Cost Calibration for Multi-Agent Target Assignment and Pathfinding
Goal-Branching LaCAM: Temporary Goals as Search Branches in Dense Multi-Agent Pathfinding
Local Visibility Roadmaps in Continous Multi-agent Path Finding
Late Autumn: LLM Agents Specialize a General Multi-Robot Planner for One Warehouse
Local Solution Repair for Multi-Agent Pickup and Delivery
A Hyper-Logical View on Multi-Agent Path Planning
Bidirectionality is Necessary in Cellular Machines for Exact-Arrival Multi-Agent Path Finding
A GPU-Resident Pipeline for Multi-Robot 3D Inspection with Limited Perception
Map-Distribution Mixture-of-Experts for Multi-Agent Pathfinding
Policy Search in Code Space for Multi-Agent Pathfinding
CARVS: A Congestion-Aware Algorithm for Online Multi-Agent Pickup-and-Delivery in Human-Collaborative Warehouses
Reinforcement Learning for Large-Scale Lifelong Multi-Agent Path Finding with Shared Spatial Fields
The Cost of Classical Multi-Agent Path Finding
Shared-Roadmap Generation and Evaluator for Multi-Agent Path Planning Using Heterogeneous Graph Neural Network
Training-Free Diffusion Planning with Analytical Local Scores
Belief-Aware Multi-Agent Path Finding under Map Uncertainty
Divide and Collapse: MAPF-Collapse via Exact Decomposition into Independent Sub-Instances
GuardPIBT: Counterfactually Gated Neural Guidance for Ultra-Large-Scale 3D Multi-Agent Path Finding
https://guardpibt.github.io/GuardPIBT/}.