Metraipolis › archive › dc_df03978fdc32
MA-WAM: Multi-Agent World-Action Model for Test-Time Planning — arXiv:2609.31281
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31281
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T01:38:40.054Z
- SHA-256 of the archived text
91e1a35c13db388f952de981cf4ac13c2297d2af4a0603bf390e872fdd10c7c8- Stable URL of this page
https://metraipolis.com/documento/dc_df03978fdc32
How to cite
MA-WAM: Multi-Agent World-Action Model for Test-Time Planning — arXiv:2609.31281 — arXiv (en), https://arxiv.org/abs/2609.31281 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df03978fdc32 (Metraipolis archive dc_df03978fdc32, sha256 91e1a35c13db388f952de981cf4ac13c2297d2af4a0603bf390e872fdd10c7c8)
BibTeX
@misc{dcdf03978fdc32,
title = {MA-WAM: Multi-Agent World-Action Model for Test-Time Planning — arXiv:2609.31281},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31281},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df03978fdc32; sha256 91e1a35c13db388f952de981cf4ac13c2297d2af4a0603bf390e872fdd10c7c8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31281. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-agent cooperative tasks require different agents to execute a joint action simultaneously, and each agent's action affects both the observations and responses of the other agents. Hence, a world model is needed to predict the team return resulting from the joint actions of all agents. A naive extension directly applies a single-agent world model to each agent's action when predicting the team return step by step. However, such an extension fails to capture the dependencies among the simultaneous actions of multiple agents. We propose Multi-Agent World-Action Model (MA-WAM), a test-time planning framework that enables a frozen multi-agent flow policy to evaluate futures of candidate joint actions. To our knowledge, MA-WAM is the first test-time world-model planner for multi-agent flow policies. MA-WAM predicts the consequences of each joint action according to cross-agent dependencies and enables efficient candidate scoring. Across 30 offline multi-agent reinforcement learning (MARL) settings on MAMuJoCo, SMAC, and MPE, MA-WAM achieves mean relative gains of 22.0% over direct execution and 25.6% over uniform action selection. Under the standard evaluation protocol on an A100 GPU, MA-WAM adds 12.1 ms, accounting for 2.5% of the measured generation-and-scoring time. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.31281 — 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 2026-10-08T01:12:14.366Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).