Strategic Algorithmic Monoculture:Experimental Evidence from Coordination Games

Computer Science > Artificial Intelligence [Submitted on 10 Apr 2026] Strategic Algorithmic Monoculture:Experimental Evidence from Coordination Games Gonzalo Ballestero, Hadi Hosseini, Samarth Khanna, Ran I. Shorrer AI agents increasingly operate in multi-agent environments where outcomes depend on coordination. We distinguish primary algorithmic monoculture -- baseline action similarity -- from strategic algorithmic monoculture, whereby agents adjust similarity in response to incentives. We implement a simple experimental design that cleanly separates these forces, and deploy it on human and large language model (LLM) subjects. LLMs exhibit high levels of baseline similarity (primary monoculture) and, like humans, they regulate it in response to coordination incentives (strategic monoculture). While LLMs coordinate extremely well on similar actions, they lag behind humans in sustaining heterogeneity when divergence is rewarded. Subjects: Artificial Intelligence (cs.AI); Computer Science and Game Theory (cs.GT); Multiagent Systems (cs.MA); Theoretical Economics (econ.TH) Cite as: arXiv:2604.09502 [cs.AI]   (or arXiv:2604.09502v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.09502 Focus to learn more Submission history From: Samarth Khanna [view email] [v1] Fri, 10 Apr 2026 17:14:46 UTC (4,695 KB) Access Paper: view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.GT cs.MA econ econ.TH 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?)