{"type":"ScholarlyArticle","title":"DIRECT: Decentralized Intention and Latent Rule Emergence for Multi-Agent Cooperation Under Intermittent Communication","authors":[{"name":"Enguang Yao","slug":"enguang-yao","given":"Enguang","family":"Yao","affiliation":""},{"name":"Qidong Liu","slug":"qidong-liu","given":"Qidong","family":"Liu","affiliation":""},{"name":"Jialu Sun","slug":"jialu-sun","given":"Jialu","family":"Sun","affiliation":""},{"name":"Kaibo Huang","slug":"kaibo-huang","given":"Kaibo","family":"Huang","affiliation":""},{"name":"Mingliang Xu","slug":"mingliang-xu","given":"Mingliang","family":"Xu","affiliation":""}],"abstract":"Most of the existing decentralized multi-agent systems facilitate coordination by achieving consensus. However, reaching global consensus among a large number of agents in complex settings is challenging because resolving a local disagreement often triggers cascading adjustments across the system. This problem is further exacerbated under intermittent communication. In the field of transportation, human drivers usually rely on intentions (e.g., turn signals) in conjunction with traffic rules (such as \"yielding to through traffic\") to achieve efficient cooperation, instead of establishing consensus with all surrounding vehicles. Inspired by this observation, we propose the Intention \\otimes Latent Rule paradigm to facilitate coordination beyond consensus, which is instantiated by DIRECT (Decentralized Intention and Latent Rule Emergence Cooperation). Within this framework, agents forecast their intentions based on current actions, and the latent rule inference module derives latent-rule representations from available information to regulate competing intentions, enabling cooperative action selection even when communication is disrupted. Extensive experiments on challenging StarCraft II micromanagement and Multi-Agent Particle Environments demonstrate that DIRECT consistently outperforms state-of-the-art methods, achieving more robust coordination across a range of communication-degraded scenarios. Our code is available at https://github.com/AAI-ZZU/DIRECT-master.","doi":"10.24963/ijcai.2026/50","url":"https://ijcai.org/proceedings/2026/50","pdf":"https://ijcai.org/proceedings/2026/0050.pdf","markdown":"https://ijcai.org/proceedings/2026/50.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/50","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Agent-based and Multi-agent Systems","track":"Main Track","number":50,"pages":{"first":437,"last":445},"keywords":["Agent-based and Multi-agent Systems: Coordination and cooperation","Machine Learning: Multiagent Reinforcement Learning","Agent-based and Multi-agent Systems: Multi-agent learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}