English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Agent-based modeling has been around for decades, and applied widely acrossthe social and natural sciences. The scope of this research method is nowpoised to grow dramatically as it absorbs the new affordances provided by LargeLanguage Models (LLM)s. Generative Agent-Based Models (GABM) are not justclassic Agent-Based Models (ABM)s where the agents talk to one another. Rather,GABMs are constructed using an LLM to apply common sense to situations, act"reasonably", recall common semantic knowledge, produce API calls to controldigital technologies like apps, and communicate both within the simulation andto researchers viewing it from the outside. Here we present Concordia, alibrary to facilitate constructing and working with GABMs. Concordia makes iteasy to construct language-mediated simulations of physically- ordigitally-grounded environments. Concordia agents produce their behavior usinga flexible component system which mediates between two fundamental operations:LLM calls and associative memory retrieval. A special agent called the GameMaster (GM), which was inspired by tabletop role-playing games, is responsiblefor simulating the environment where the agents interact. Agents take actionsby describing what they want to do in natural language. The GM then translatestheir actions into appropriate implementations. In a simulated physical world,the GM checks the physical plausibility of agent actions and describes theireffects. In digital environments simulating technologies such as apps andservices, the GM may handle API calls to integrate with external tools such asgeneral AI assistants (e.g., Bard, ChatGPT), and digital apps (e.g., Calendar,Email, Search, etc.). Concordia was designed to support a wide array ofapplications both in scientific research and for evaluating performance of realdigital services by simulating users and/or generating synthetic data.

Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia