{"id":1064877,"date":"2024-08-02T12:11:11","date_gmt":"2024-08-02T19:11:11","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&p=1064877"},"modified":"2024-08-07T13:55:55","modified_gmt":"2024-08-07T20:55:55","slug":"emergence","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/emergence\/","title":{"rendered":"Emergence"},"content":{"rendered":"
\n\t
\n\t\t
\n\t\t\t\"Creators,\t\t<\/div>\n\t\t\n\t\t
\n\t\t\t\n\t\t\t
\n\t\t\t\t\n\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n

Emergence<\/h2>\n\n\n\n

Creators, players and AI models collaboratively build and evolve games over time <\/p>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n

In this project, we explore how game creators, players and generative AI models can collaboratively build and continually evolve games over time. We are currently looking at game narratives and non-player character definitions and dialogues, but eventually hope to apply this paradigm to the creation of entire game worlds.<\/p>\n\n\n\n

In our paper \u201cPlayer-Driven Emergence in LLM-Driven Game Narrative<\/a>,\u201d presented at IEEE Conference on Games 2024, we explore how large language models can foster unique forms of creativity when players participate in the narrative design process. Rather than replacing designers, LLMs can empower players with considerable freedom in their interactions with nonplayer characters (NPC). We show how these interactions provide implicit feedback for designers, offering insights unattainable with traditional dialogue trees.<\/p>\n\n\n\n

In our paper \u201cGENEVA: GENErating and Visualizing branching narratives using LLMs (opens in new tab)<\/span><\/a>,\u201d presented at IEEE Conference on Games 2024, we introduce a graph-based narrative generation and visualization tool. This tool requires as input a high-level narrative description and constraints, such as the number of different starts, endings, and storylines, as well as context for grounding the narrative. Given these inputs, GENEVA then goes on to use the generative capabilities of GPT-4 to create narratives with branching storylines and renders them in a graph format, allowing users to interactively explore different narrative paths through its web interface (opens in new tab)<\/span><\/a>.<\/p>\n\n\n\n

<\/div>\n\n\n","protected":false},"excerpt":{"rendered":"

Creators, players and AI models collaboratively build and evolve games over time In this project, we explore how game creators, players and generative AI models can collaboratively build and continually evolve games over time. We are currently looking at game narratives and non-player character definitions and dialogues, but eventually hope to apply this paradigm to […]<\/p>\n","protected":false},"featured_media":1065669,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13556,13545],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1064877","msr-project","type-msr-project","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-research-area-human-language-technologies","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"","related-publications":[1035108,1045470,1053801,1013550],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Sudha Rao","user_id":38341,"people_section":"Related people","alias":"sudhra"},{"type":"user_nicename","display_name":"Weijia Xu","user_id":42636,"people_section":"Related people","alias":"weijiaxu"},{"type":"user_nicename","display_name":"Nebojsa Jojic","user_id":32384,"people_section":"Related people","alias":"jojic"},{"type":"user_nicename","display_name":"Michael Xu","user_id":41979,"people_section":"Related people","alias":"michaelxu"},{"type":"user_nicename","display_name":"Jorge Leandro","user_id":42261,"people_section":"Related people","alias":"jorgeleandro"},{"type":"user_nicename","display_name":"Chris Brockett","user_id":31423,"people_section":"Related people","alias":"chrisbkt"},{"type":"user_nicename","display_name":"Bill Dolan","user_id":31229,"people_section":"Related people","alias":"billdol"}],"msr_research_lab":[199565],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1064877"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":13,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1064877\/revisions"}],"predecessor-version":[{"id":1067067,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1064877\/revisions\/1067067"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/1065669"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1064877"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1064877"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1064877"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1064877"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1064877"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}