Search papers, labs, and topics across Lattice.
The paper introduces ARMATA, a centralized, end-to-end autoregressive framework for multi-agent task assignment that jointly optimizes area allocation and routing. ARMATA uses a multi-stage decoding mechanism to unify high-level allocation and low-level routing within a single autoregressive pass, enabling the model to balance workload distribution and routing efficiency. Experiments show ARMATA outperforms industrial solvers like Google OR-Tools, IBM CPLEX, and LKH-3 by up to 20% in solution quality, while also reducing computation time significantly.
End-to-end learning can beat even the best industrial solvers at multi-agent task assignment, improving solution quality by 20% while slashing computation time from hours to seconds.
Coordinating multi-agent systems over spatially distributed areas requires solving a complex hierarchical problem: first distributing areas among agents (allocation) and subsequently determining the optimal visitation order (routing). Existing methods typically decouple these stages ignoring inter-stage dependencies or rely on decentralized heuristics that lack global context. In this work, we propose a centralized, fully end-to-end auto-regressive framework that jointly generates allocation decisions and routing sequences. The core contribution of our approach is a multi-stage decoding mechanism that unifies high-level allocation and low-level routing in a single autoregressive pass while maintaining a centralized global state. This enables the model to implicitly balance workload distribution with routing efficiency, avoiding local optima common in decentralized methods. Extensive experiments demonstrate that our method significantly outperforms diverse baselines, achieving up to a 20\% improvement in solution quality over industrial solvers such as Google OR-Tools, IBM CPLEX, and LKH-3, while reducing computation time from hours to seconds.