{"id":311460,"date":"2025-12-12T05:29:10","date_gmt":"2025-12-12T05:29:10","guid":{"rendered":"https:\/\/www.newsbeep.com\/uk\/311460\/"},"modified":"2025-12-12T05:29:10","modified_gmt":"2025-12-12T05:29:10","slug":"build-with-gemini-deep-research","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/uk\/311460\/","title":{"rendered":"Build with Gemini Deep Research"},"content":{"rendered":"<p data-block-key=\"o711n\">Today, we are releasing a significantly more powerful <a href=\"https:\/\/ai.google.dev\/gemini-api\/docs\/deep-research\" rel=\"nofollow noopener\" target=\"_blank\">Gemini Deep Research agent<\/a>, available via the <a href=\"https:\/\/blog.google\/technology\/developers\/interactions-api\" rel=\"nofollow noopener\" target=\"_blank\">Interactions API<\/a>. For the first time, developers can embed Google\u2019s most advanced autonomous research capabilities directly into their own applications. We are also open-sourcing a new web research agent benchmark, DeepSearchQA, designed to test agent comprehensiveness on web research tasks.<\/p>\n<p data-block-key=\"adc2s\">Gemini Deep Research is an agent optimized for long-running context gathering and synthesis tasks. The agent\u2019s reasoning core uses <a href=\"https:\/\/blog.google\/products\/gemini\/gemini-3\/\" rel=\"nofollow noopener\" target=\"_blank\">Gemini 3 Pro<\/a>, our <a href=\"https:\/\/deepmind.google\/blog\/facts-benchmark-suite-systematically-evaluating-the-factuality-of-large-language-models\/\" rel=\"nofollow noopener\" target=\"_blank\">most factual model<\/a> yet, and is specifically trained to reduce hallucinations and maximize report quality during complex tasks. By scaling multi-step reinforcement learning for search, the agent autonomously navigates complex information landscapes with high accuracy.<\/p>\n<p data-block-key=\"eb77m\">Deep Research iteratively plans its investigation \u2013 it formulates queries, reads results, identifies knowledge gaps, and searches again. This release features vastly improved web search, allowing it to navigate deep into sites for specific data.<\/p>\n<p data-block-key=\"75vee\">The new Gemini Deep Research agent achieves state-of-the-art results on <a href=\"https:\/\/arxiv.org\/abs\/2501.14249\" rel=\"nofollow noopener\" target=\"_blank\">Humanity\u2019s Last Exam<\/a> (HLE) and DeepSearchQA, and is our best on <a href=\"https:\/\/openai.com\/index\/browsecomp\/\" rel=\"nofollow noopener\" target=\"_blank\">BrowseComp<\/a>. It is optimized to generate well-researched reports at much lower <a href=\"https:\/\/ai.google.dev\/gemini-api\/docs\/pricing#pricing-for-agents\" rel=\"nofollow noopener\" target=\"_blank\">cost<\/a>. Deep Research is now more useful and intelligent than ever, and will soon be available in <a href=\"https:\/\/blog.google\/products\/search\/google-search-ai-mode-update\/#deep-search\" rel=\"nofollow noopener\" target=\"_blank\">Google Search<\/a>, <a href=\"https:\/\/blog.google\/technology\/google-labs\/notebooklm-deep-research-file-types\/\" rel=\"nofollow noopener\" target=\"_blank\">NotebookLM<\/a>, <a href=\"https:\/\/blog.google\/products\/search\/new-google-finance-ai-deep-search\/\" rel=\"nofollow noopener\" target=\"_blank\">Google Finance<\/a> and upgraded in the <a href=\"https:\/\/gemini.google\/overview\/deep-research\/\" rel=\"nofollow noopener\" target=\"_blank\">Gemini App<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"Today, we are releasing a significantly more powerful Gemini Deep Research agent, available via the Interactions API. For&hellip;\n","protected":false},"author":2,"featured_media":311461,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[554,733,4308,3085,86,56,54,55],"class_list":{"0":"post-311460","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-artificial-intelligence","10":"tag-artificialintelligence","11":"tag-none","12":"tag-technology","13":"tag-uk","14":"tag-united-kingdom","15":"tag-unitedkingdom"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/311460","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/comments?post=311460"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/311460\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media\/311461"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media?parent=311460"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/categories?post=311460"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/tags?post=311460"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}