Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization

Combinatorial optimization problems involving multiple agents are notoriously challenging due to their NP-hard nature and the necessity for effective agent coordination. Despite advancements in learning-based methods, existing approaches often face critical limitations, including suboptimal agent coordination, poor generalizability, and high computational latency. To address these issues, we propose Parallel AutoRegressive Combinatorial Optimization (PARCO), a reinforcement learning framework designed to construct high-quality solutions for multi-agent combinatorial tasks efficiently. To this end, PARCO integrates three key components: (1) transformer-based communication layers to enable effective agent collaboration during parallel solution construction, (2) a multiple pointer mechanism for low-latency, parallel agent decision-making, and (3) priority-based conflict handlers to resolve decision conflicts via learned priorities. We evaluate PARCO in multi-agent vehicle routing and scheduling problems where our approach outperforms state-of-the-art learning methods and demonstrates strong generalization ability and remarkable computational efficiency. Code available at:this https URL.

@article{berto2025_2409.03811,
  title={ Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization },
  author={ Federico Berto and Chuanbo Hua and Laurin Luttmann and Jiwoo Son and Junyoung Park and Kyuree Ahn and Changhyun Kwon and Lin Xie and Jinkyoo Park },
  journal={arXiv preprint arXiv:2409.03811},
  year={ 2025 }
}