EUVIMEDEUVIMED entdecken
Crossref

Towards Low-Dimensional Search for Mastering Multi-Agent Planning

Sizhe Tang, Yu Li, Mahdi Imani, Tian Lan

Proceedings of the AAAI Symposium Series · 18.05.2026 · 8 (1) · 613-617

DOI: 10.1609/aaaiss.v8i1.42596 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 18.05.2026. Verfasst von Sizhe Tang und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Monte Carlo Tree Search (MCTS) faces a severe scalability bottleneck in Multi-Agent Planning (MAP) due to the combinatorial explosion of joint action spaces. In this position paper, we argue that the key to tractable planning lies in leveraging low-dimensional representational structures to guide the tree search, rather than enumerating the raw action space. Specifically, under a linear approximation of joint-action returns, we demonstrate that the node expansion problem can be effectively cast and solved as a linear contextual bandit, providing theoretical regret guarantees. Empirical results on complex benchmarks confirm that this structure-aware search significantly outperforms state-of-the-art baselines, offering a scalable path for neuro-symbolic multi-agent planning. We further discuss promising extensions, including integrating dynamic agent grouping and coalition formation mechanisms to further reduce the effective branching factor.

Zitieren

APA

Tang, S., Li, Y., Imani, M., & Lan, T. (2026). Towards Low-Dimensional Search for Mastering Multi-Agent Planning. Proceedings of the AAAI Symposium Series, 8(1), 613-617. https://doi.org/10.1609/aaaiss.v8i1.42596

Vancouver

Tang S, Li Y, Imani M, Lan T. Towards Low-Dimensional Search for Mastering Multi-Agent Planning. Proceedings of the AAAI Symposium Series. 2026;8(1):613-617. doi:10.1609/aaaiss.v8i1.42596

BibTeX
@article{Tang2026,
  author = {Tang, Sizhe and Li, Yu and Imani, Mahdi and Lan, Tian},
  title = {Towards Low-Dimensional Search for Mastering Multi-Agent Planning},
  journal = {Proceedings of the AAAI Symposium Series},
  year = {2026},
  volume = {8},
  number = {1},
  pages = {613--617},
  doi = {10.1609/aaaiss.v8i1.42596}
}
Kostenlos starten →