Metraipolis › archive › dc_6338afa3ffad
GeoPAR: Large-Scale Multi-Agent Combinatorial Optimization with Geometry-Guided Parallel Autoregressive Learning — arXiv:2609.00577
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00577
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:33:31.182Z
- SHA-256 of the archived text
d01e9c58075dc052337a916a3bbe81bacf780c96b08a1a92632581f46addc507- Stable URL of this page
https://metraipolis.com/documento/dc_6338afa3ffad
How to cite
GeoPAR: Large-Scale Multi-Agent Combinatorial Optimization with Geometry-Guided Parallel Autoregressive Learning — arXiv:2609.00577 — arXiv (en), https://arxiv.org/abs/2609.00577 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6338afa3ffad (Metraipolis archive dc_6338afa3ffad, sha256 d01e9c58075dc052337a916a3bbe81bacf780c96b08a1a92632581f46addc507)
BibTeX
@misc{dc6338afa3ffad,
title = {GeoPAR: Large-Scale Multi-Agent Combinatorial Optimization with Geometry-Guided Parallel Autoregressive Learning — arXiv:2609.00577},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00577},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6338afa3ffad; sha256 d01e9c58075dc052337a916a3bbe81bacf780c96b08a1a92632581f46addc507},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00577. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-agent combinatorial optimization problems are notoriously challenging due to their NP-hard nature. Recent parallel autoregressive neural solvers improve inference efficiency by allowing agents to make decisions simultaneously, but their performance often degrades on large-scale instances. This is largely attributable to weak modeling of local geometric structures and the fact that conflicting task selections are handled only after action generation. To address these limitations, we propose GeoPAR, a geometry-guided parallel autoregressive reinforcement learning framework for scalable multi-agent combinatorial optimization. GeoPAR integrates three key components: (1) a projection-window sparse geometry mechanism that builds lightweight local candidate neighborhoods through multi-directional projections, (2) sparse edge-biased attention that injects these geometric relations into node representations, and (3) cache-guided conflict-aware assignment that reuses the geometric cache during decoding to suppress duplicate selections of exclusive tasks. Experiments on heterogeneous vehicle routing and open multi-depot pickup-and-delivery problems show that GeoPAR improves large-scale zero-shot generalization while substantially reducing rollout steps and maintaining efficient inference. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE). Pagina del lavoro: https://arxiv.org/abs/2609.00577 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T06:15:12.803Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).