Multi-Agent Empowerment and Emergence of Complex Behavior in Groups

Computer Science > Artificial Intelligence [Submitted on 22 Apr 2026] Multi-Agent Empowerment and Emergence of Complex Behavior in Groups Tristan Shah, Ilya Nemenman, Daniel Polani, Stas Tiomkin Intrinsic motivations are receiving increasing attention, i.e. behavioral incentives that are not engineered, but emerge from the interaction of an agent with its surroundings. In this work we study the emergence of behaviors driven by one such incentive, empowerment, specifically in the context of more than one agent. We formulate a principled extension of empowerment to the multi-agent setting, and demonstrate its efficient calculation. We observe that this intrinsic motivation gives rise to characteristic modes of group-organization in two qualitatively distinct environments: a pair of agents coupled by a tendon, and a controllable Vicsek flock. This demonstrates the potential of intrinsic motivations such as empowerment to not just drive behavior for only individual agents but also higher levels of behavioral organization at scale. Comments: 11 pages Subjects: Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) ACM classes: I.2.11 Cite as: arXiv:2604.21155 [cs.AI]   (or arXiv:2604.21155v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.21155 Focus to learn more Submission history From: Tristan Shah [view email] [v1] Wed, 22 Apr 2026 23:51:04 UTC (16,134 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.MA References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation 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 Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)