[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82707-en":3,"doc-seo-82707-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},82707,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Microcosmos: Reimagining Artificial Life for the GPU Era","Microcosmos presents a GPU-ready artificial life simulation engine that models lifeforms as elastic filament chains in a two-dimensional viscous fluid world. The simulator targets end-to-end differentiable dynamics and addresses two field bottlenecks: missing physical grounding and limited scalability for large-population evolutionary search. Validation covers physical constraint-respecting fluid coupling, gradient-based filament folding with full differentiability, and neuroevolution/quality-diversity discovery of swimming and chemotaxis. Linear scaling with particle count supports large-scale runs. An open platform aims at long-term open-ended evolution that remains physically plausible and computationally scalable.","arXiv :2607 .02954v 1 [ cs .NE] 3 Jul 2026  \nMicrocosmos: Reimagining Artificial Life for the GPU Era  \nMark Tensen 1 ,∗ , Ciaran Regan 1 ,2 ,3 , Bert Wang-Chak Chan 1 , Mizuki Oka 1 ,4 , Kenneth O. Stanley5 , and Grisha Szep 1 ,4  \n1Artificial Life Institute, Japan  \n2 Sakana AI, Japan  \n3University of Tsukuba, Japan  \n4 Chiba Institute of Technology, Japan  \n5Lila Sciences, USA  \n∗[mark.tensen@alife.institute](mark.tensen@alife.institute)  \nAbstract  \nMost artificial life simulators either operate on abstract substrates disconnected from physical reality, or simulate physically grounded worlds that do not scale to the population sizes required for open-ended evolution. We present Microcosmos, a simulation engine in which artificial lifeforms are modeled as elastic filament chains inhabiting a two-dimensional viscous fluid world, designed from the ground up for modern GPU hardware and end-to-end differentiable simulation. We validate the engine through four experiments. Hand-designed locomotion strategies confirm that the fluid coupling respects known physical constraints. Gradient-based optimization of filament folding demonstrates both the full differentiability of the simulator and the expressivity of the filament encodings. Neuroevolution and quality-diversity search produce a wide range of swimming and chemotaxis behaviors automatically. Linear scaling with particle count confirms the engine supports large-scale simulation. Microcosmos is released as an open platform with the long-term goal of supporting largescale open-ended evolutionary simulations, designed to be physically plausible and computationally scalable.  \nSubmission type: Full Paper  \nCode available at: [https://github.com/](https://github.com/)[ ](https://github.com/)[alife-institute/microcosmos](alife-institute/microcosmos)  \nSupplementary videos available at: [https:](https:)//[alife.institute/microcosmos-supp](alife.institute/microcosmos-supp)  \nIntroduction  \nWhat is preventing artificial life (ALife) from achieving the kind of open-ended evolutionary complexity we observe in nature? Despite decades of progress, many of the open problems identified by Bedau et al. (2000) remain unsolved. We argue that the field is held back by both a lack of physical grounding in our simulation substrates and insufficient computational scalability to support evolutionary search at scale. Abstract rule-based substrates (Langton, 1986; Chan, 2019;  \n©2026 [Mark Tensen, Ciaran Regan, Bert Wang-Chak Chan, Mizuki Oka, Kenneth O. Stanley, and Grisha Szep] . Published under a Creative Commons Attribution 4.0 International (CC BY 4.0) license.  \n(a) Filaments bend, interact and flow in a fluid field.  \n(b) Diverse swimming gaits discovered via QD search.  \nFigure 1: Microcosmos: a scalable simulator for artificial life. Individuals are modeled as flexible filaments in a simulated fluid environment. (a) The three core physics components: (i) Filaments have preferred resting shapes, able to bend and deform elastically. (ii) Self-avoidance and interbody repulsion mediated by scalar fields. (iii) Two-way coupling between individuals and the surrounding fluid. (b) Diverse swimming strategies discovered by quality-diversity search, illustrating the behavioral richness the simulator supports. See supplementary materials Figure S1a for animations.  \nRay, 1991; Alakuijala et al., 2024) are efficient to evolve but disconnected from the physical principles underlying life, as studied in fields such as biophysics and fluid dynamics. Conversely, more physically grounded simulators tend tobe computationally intractable for large scale evolutionary search (Faure et al., 2012; Nedelec and Foethke, 2007), operate at too high a level of abstraction (Heinemann, 2024; Alakuijala et al., 2024), or are designed for reinforcement learning rather than the open-ended dynamics of life (Bhatia et al., 2021; Matthews et al., 2025; Lagemann et al., 2025) . Progress demands simulators that are physically gr","cbCaietLe1G9N9Cy","https://ap.wps.com/l/cbCaietLe1G9N9Cy","pdf",5745860,2,1,10,"English","en",105,"# Abstract\n# Introduction\n## Problem: limits of existing artificial life simulators\n## Core inspiration: microscale locomotion and filament-based organization\n## Microcosmos overview","[{\"question\":\"What is Microcosmos designed to address in artificial life simulations?\",\"answer\":\"It targets the lack of physical grounding and the insufficient computational scalability of existing simulators, so evolutionary search can run at large population sizes while maintaining physical credibility.\"},{\"question\":\"How are artificial lifeforms represented in Microcosmos?\",\"answer\":\"Lifeforms are modeled as elastic filament chains with genetic encodings that specify both morphology and behavior, moving and deforming within a two-dimensional viscous fluid world.\"},{\"question\":\"What evidence supports Microcosmos’s differentiability and physical plausibility?\",\"answer\":\"Hand-designed locomotion tests verify fluid coupling respects known physical constraints, while gradient-based optimization of filament folding demonstrates full end-to-end differentiability of the simulator.\"}]",1784182410,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"microcosmos-reimagining-artificial-life-for-the-gpu-era","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/microcosmos-reimagining-artificial-life-for-the-gpu-era/82707/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is Microcosmos designed to address in artificial life simulations?","Question",{"text":75,"@type":76},"It targets the lack of physical grounding and the insufficient computational scalability of existing simulators, so evolutionary search can run at large population sizes while maintaining physical credibility.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are artificial lifeforms represented in Microcosmos?",{"text":80,"@type":76},"Lifeforms are modeled as elastic filament chains with genetic encodings that specify both morphology and behavior, moving and deforming within a two-dimensional viscous fluid world.",{"name":82,"@type":73,"acceptedAnswer":83},"What evidence supports Microcosmos’s differentiability and physical plausibility?",{"text":84,"@type":76},"Hand-designed locomotion tests verify fluid coupling respects known physical constraints, while gradient-based optimization of filament folding demonstrates full end-to-end differentiability of the simulator.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":22,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]