ARMATA: Auto-Regressive Multi-Agent Task Assignment

TL;DR

This paper introduces ARMATA, an end-to-end autoregressive framework for joint multi-agent task allocation and routing, significantly improving solution quality and efficiency over existing methods.

Contribution

It presents a novel centralized multi-stage decoding approach that unifies allocation and routing in a single autoregressive model, outperforming traditional solvers.

Findings

Achieves up to 20% better solutions than industrial solvers.

Reduces computation time from hours to seconds.

Outperforms diverse baseline methods in experiments.

Abstract

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.