{"692343":{"#nid":"692343","#data":{"type":"news","title":"Assessing Scientific Claims: Agent-Based AI System Answers Tough Questions","body":[{"value":"\u003Cp\u003EAdvances in materials science and drug discovery increasingly depend on robotic laboratories that synthesize and test candidate compounds without human intervention. Artificial intelligence models can now propose custom materials and potential drug molecules far faster than robotic labs can physically test them. The resulting pools of candidate materials dramatically outstrip the availability of experimental testing.\u003Cbr\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EDeciding which candidates deserve scarce laboratory time is itself a hard problem. It requires weighing scientific plausibility against practical constraints \u2014 likely impact, expected effectiveness, and eventual manufacturability \u2014 considerations that are difficult to apply consistently across thousands of candidates.\u003Cbr\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAn artificial intelligence (AI) program developed at the Georgia Tech Research Institute (GTRI) could provide a new way to narrow that hypothesis pool down to a rate that robotic laboratories can actually test, and more broadly, to evaluate a wide range of scientific and technical claims that would otherwise overwhelm human assessment.\u003Cbr\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EKnown as FARSCAPE, the program was developed to support a research project organized by the U.S. Defense Advanced Research Projects Agency (DARPA) to evaluate a broad range of feasibility questions. By breaking down challenging questions into smaller components that can be evaluated by a team of independent computer agents, FARSCAPE uses a \u201cchain of thought\u201d approach to provide answers in the form of probabilities. It then helps humans check the rationales for its assessment.\u003Cbr\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/gtri.gatech.edu\/newsroom\/assessing-scientific-claims-agent-based-ai-system-answers-tough-questions\u0022\u003ERead the full article\u003C\/a\u003E on the Georgia Tech Research Institute news page\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EFARSCAPE, an artificial intelligence (AI) program developed at the Georgia Tech Research Institute (GTRI) could provide a new way to evaluate a wide range of scientific and technical claims that would otherwise overwhelm human assessment.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"An artificial intelligence program developed at the Georgia Tech Research Institute could provide a new way to evaluate scientific claims."}],"uid":"27303","created_gmt":"2026-09-04 14:48:35","changed_gmt":"2026-09-04 14:54:00","author":"John Toon","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-09-04T00:00:00-04:00","iso_date":"2026-09-04T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"681071":{"id":"681071","type":"image","title":"FARSCAPE provides a new way to evaluate a wide range of scientific and technical claims","body":"\u003Cp\u003EFARSCAPE provides a new way to evaluate a wide range of scientific and technical claims. The chart shows the step-by-step process.\u003C\/p\u003E","created":"1788532464","gmt_created":"2026-09-04 14:34:24","changed":"1788532744","gmt_changed":"2026-09-04 14:39:04","alt":"User looking at FARSCAPE process diagram on a screen","file":{"fid":"265423","name":"farscape_mockup.jpg","image_path":"\/sites\/default\/files\/2026\/09\/04\/farscape_mockup.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/09\/04\/farscape_mockup.jpg","mime":"image\/jpeg","size":2231564,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/09\/04\/farscape_mockup.jpg?itok=932ef0ir"}}},"media_ids":["681071"],"groups":[{"id":"1188","name":"Research Horizons"}],"categories":[{"id":"194606","name":"Artificial Intelligence"}],"keywords":[{"id":"187915","name":"go-researchnews"}],"core_research_areas":[{"id":"193655","name":"Artificial Intelligence at Georgia Tech"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003Egtri.media@gtri.gatech.edu\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}