Decentralized Collective World Model for Emergent Communication and Coordination

[2504.03353] Decentralized Collective World Model for Emergent Communication and Coordination Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Multiagent Systems arXiv:2504.03353 (cs) [Submitted on 4 Apr 2025 ( v1 ), last revised 7 Oct 2025 (this version, v3)] Title: Decentralized Collective World Model for Emergent Communication and Coordination Authors: Kentaro Nomura , Tatsuya Aoki , Tadahiro Taniguchi , Takato Horii View a PDF of the paper titled Decentralized Collective World Model for Emergent Communication and Coordination, by Kentaro Nomura and 3 other authors View PDF HTML (experimental) Abstract: We propose a fully decentralized multi-agent world model that enables both symbol emergence for communication and coordinated behavior through temporal extension of collective predictive coding. Unlike previous research that focuses on either communication or coordination separately, our approach achieves both simultaneously. Our method integrates world models with communication channels, enabling agents to predict environmental dynamics, estimate states from partial observations, and share critical information through bidirectional message exchange with contrastive learning for message alignment. Using a two-agent trajectory drawing task, we demonstrate that our communication-based approach outperforms non-communicative models when agents have divergent perceptual capabilities, achieving the second-best coordination after centralized models. Importantly, our decentralized approach with constraints preventing direct access to other agents' internal states facilitates the emergence of more meaningful symbol systems that accurately reflect environmental states. These findings demonstrate the effectiveness of decentralized communication for supporting coordination while developing shared representations of the environment. Comments: Accepted at IEEE ICDL 2025 Subjects: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2504.03353 [cs.MA] (or arXiv:2504.03353v3 [cs.MA] for this version) https://doi.org/10.48550/arXiv.2504.03353 Focus to learn more arXiv-issued DOI via DataCite Related DOI : https://doi.org/10.1109/ICDL63968.2025.11204457 Focus to learn more DOI(s) linking to related resources Submission history From: Kentaro Nomura [ view email ] [v1] Fri, 4 Apr 2025 11:17:52 UTC (1,354 KB) [v2] Thu, 19 Jun 2025 07:49:54 UTC (854 KB) [v3] Tue, 7 Oct 2025 13:35:49 UTC (854 KB) Full-text links: Access Paper: View a PDF of the paper titled Decentralized Collective World Model for Emergent Communication and Coordination, by Kentaro Nomura and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.MA < prev | next > new | recent | 2025-04 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• The interdisciplinary study of coordination#6617
• Cognitive constraints govern collective outcomes in strategic network formation#1167874
• Cognitive constraints govern collective outcomes in strategic network formation#1148190
• Role differentiation as ignition of a collective information engine: Structuration in Agent Populations#998396
• The Cost of Coordination: Why Multi-Agent LLMs Explore More But Discover Less#368869