{"id":1155401,"date":"2025-12-04T04:12:57","date_gmt":"2025-12-04T12:12:57","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&p=1155401"},"modified":"2025-12-15T03:16:25","modified_gmt":"2025-12-15T11:16:25","slug":"visual-episodic-memory-and-use-in-agentic-systems","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/visual-episodic-memory-and-use-in-agentic-systems\/","title":{"rendered":"Visual episodic memory and use in agentic systems"},"content":{"rendered":"
\n\t
\n\t\t
\n\t\t\t\"background\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

Visual episodic memory and use in agentic systems<\/h1>\n\n\n\n

<\/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

Human intelligence is defined by the interplay of semantic and episodic memory. AI research almost exclusively develops semantic memory systems, but episodic memory has many open challenges, especially for vision. Episodic memory is the ability to recall specific past experiences and use the information together with semantic memory to interact and solve problems. By providing AI with episodic memory, we will enable agents that are grounded in a place and time, able to gain expertise in their environment and workflow, and to build experience with people around them.<\/p>\n\n\n\n

This research is conducted via\u00a0The Agentic AI Research and Innovation\u00a0<\/a>(AARI) Initiative which focuses on the next frontier of agentic systems through\u00a0Grand Challenges<\/em>\u00a0with the academic community and Microsoft Research.<\/p>\n\n\n","protected":false},"excerpt":{"rendered":"

Human intelligence is defined by the interplay of semantic and episodic memory. AI research almost exclusively develops semantic memory systems, but episodic memory has many open challenges, especially for vision. Episodic memory is the ability to recall specific past experiences and use the information together with semantic memory to interact and solve problems. By providing […]<\/p>\n","protected":false},"featured_media":1155703,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13556],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1155401","msr-project","type-msr-project","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"","related-publications":[],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"guest","display_name":"Derek Hoiem","user_id":1157419,"people_section":"Section name 0","alias":""},{"type":"user_nicename","display_name":"Reuben Tan","user_id":43827,"people_section":"Section name 0","alias":"tanreuben"},{"type":"guest","display_name":"Yao Xiao","user_id":1157420,"people_section":"Section name 0","alias":""}],"msr_research_lab":[],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1155401","targetHints":{"allow":["GET"]}}],"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":4,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1155401\/revisions"}],"predecessor-version":[{"id":1158523,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1155401\/revisions\/1158523"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/1155703"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1155401"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1155401"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1155401"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1155401"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1155401"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}