{"id":180,"date":"2025-05-31T22:06:00","date_gmt":"2025-05-31T22:06:00","guid":{"rendered":"https:\/\/genia.inaf.it\/?p=180"},"modified":"2026-04-24T22:08:31","modified_gmt":"2026-04-24T22:08:31","slug":"hypotesis-generation-verification","status":"publish","type":"post","link":"https:\/\/genia.inaf.it\/?p=180","title":{"rendered":"Hypotesis generation &amp; verification"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">Exp-Bench (P.T.J.Kon et al., 06.2025) &#8211;&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/2505.24785\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/arxiv.org\/abs\/2505.24785<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">NovelSeek &#8211; Building Closed-Loop System from Hypothesis to Verification&nbsp;<a href=\"https:\/\/alpha-innovator.github.io\/NovelSeek-project-page\/\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/alpha-innovator.github.io\/NovelSeek-project-page\/<\/a>&nbsp;(B.Zhang et al., 05.2025) &#8211;&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/2505.16938\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/arxiv.org\/abs\/2505.16938<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">AI-Researcher: Autonomous Scientific Innovation&nbsp;<a href=\"https:\/\/github.com\/HKUDS\/AI-Researcher\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/github.com\/HKUDS\/AI-Researcher<\/a>&nbsp;(J.Tang et al., 05.2025) &#8211;&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/2505.18705\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/arxiv.org\/abs\/2505.18705<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">ML-Agent: Reinforcing LLM Agents for Autonomous ML Engineering (Z.Liu et al., 05.2025) &#8211;&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/2505.23723\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/arxiv.org\/abs\/2505.23723<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The AI Scientist-v2&nbsp;<a href=\"https:\/\/github.com\/SakanaAI\/AI-Scientist-v2\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/github.com\/SakanaAI\/AI-Scientist-v2<\/a>&nbsp;(Y.Yamada et al., 04.2025) &#8211;&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/2504.08066\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/arxiv.org\/abs\/2504.08066<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedback&nbsp;<a href=\"https:\/\/alpha-innovator.github.io\/Dolphin-project-page\/\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/alpha-innovator.github.io\/Dolphin-project-page\/<\/a>&nbsp;(J.Yuan et al., 04.2025) &#8211;&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/2501.03916\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/arxiv.org\/abs\/2501.03916<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Sparks of Science: Hypothesis Generation Using Structured Paper Data (C.O&#8217;Neill et al., 04.2025) &#8211;&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/2504.12976\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/arxiv.org\/abs\/2504.12976<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">A Survey on Hypothesis Generation for Scientific Discovery in the Era of LLMs (A.K.Alkan et al., 04.2025) &#8211;&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/2504.05496v1\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/arxiv.org\/abs\/2504.05496v1<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Can LLMs generate novel research ideas? (C.Li et al., 09.2024) &#8211;&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/2409.04109\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/arxiv.org\/abs\/2409.04109<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The AI Scientist v1&nbsp;<a href=\"https:\/\/github.com\/SakanaAI\/AI-Scientist\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/github.com\/SakanaAI\/AI-Scientist<\/a>&nbsp;(C.Lu et al., 08.2024) &#8211;&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/2408.06292\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/arxiv.org\/abs\/2408.06292<\/a>&nbsp;&#8211;&nbsp;<a href=\"https:\/\/sakana.ai\/ai-scientist\/\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/sakana.ai\/ai-scientist\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Exp-Bench (P.T.J.Kon et al., 06.2025) &#8211;&nbsp;https:\/\/arxiv.org\/abs\/2505.24785 NovelSeek &#8211; Building Closed-Loop System from Hypothesis to Verification&nbsp;https:\/\/alpha-innovator.github.io\/NovelSeek-project-page\/&nbsp;(B.Zhang et al., 05.2025) &#8211;&nbsp;https:\/\/arxiv.org\/abs\/2505.16938 AI-Researcher: Autonomous Scientific Innovation&nbsp;https:\/\/github.com\/HKUDS\/AI-Researcher&nbsp;(J.Tang et al., 05.2025) &#8211;&nbsp;https:\/\/arxiv.org\/abs\/2505.18705 ML-Agent: Reinforcing LLM Agents for Autonomous ML Engineering (Z.Liu et al., 05.2025) &#8211;&nbsp;https:\/\/arxiv.org\/abs\/2505.23723 The AI Scientist-v2&nbsp;https:\/\/github.com\/SakanaAI\/AI-Scientist-v2&nbsp;(Y.Yamada et al., 04.2025) &#8211;&nbsp;https:\/\/arxiv.org\/abs\/2504.08066 Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice,&hellip;&nbsp;<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"neve_meta_sidebar":"","neve_meta_container":"","neve_meta_enable_content_width":"","neve_meta_content_width":0,"neve_meta_title_alignment":"","neve_meta_author_avatar":"","neve_post_elements_order":"","neve_meta_disable_header":"","neve_meta_disable_footer":"","neve_meta_disable_title":"","_themeisle_gutenberg_block_has_review":false,"footnotes":""},"categories":[7],"tags":[],"class_list":["post-180","post","type-post","status-publish","format-standard","hentry","category-science-agents"],"acf":[],"_links":{"self":[{"href":"https:\/\/genia.inaf.it\/index.php?rest_route=\/wp\/v2\/posts\/180","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/genia.inaf.it\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/genia.inaf.it\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/genia.inaf.it\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/genia.inaf.it\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=180"}],"version-history":[{"count":1,"href":"https:\/\/genia.inaf.it\/index.php?rest_route=\/wp\/v2\/posts\/180\/revisions"}],"predecessor-version":[{"id":181,"href":"https:\/\/genia.inaf.it\/index.php?rest_route=\/wp\/v2\/posts\/180\/revisions\/181"}],"wp:attachment":[{"href":"https:\/\/genia.inaf.it\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=180"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/genia.inaf.it\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=180"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/genia.inaf.it\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=180"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}