Step 4: tool results

read_page

{
  "url": "https://arxiv.org/abs/2502.18864",
  "max_chars": 4000
}

{"ok":true,"url":"https://arxiv.org/abs/2502.18864","text":"[2502.18864] Accelerating scientific discovery with Co-Scientist\nSkip to main content\nSearch\nSubmit\nDonate\nLog in\nSearch arXiv\nPress Enter to search · Advanced search\n-->\nComputer Science > Artificial Intelligence\narXiv:2502.18864 (cs)\n[Submitted on 26 Feb 2025 ( v1 ), last revised 29 Jun 2026 (this version, v2)]\nTitle: Accelerating scientific discovery with Co-Scientist\nAuthors: Juraj Gottweis , Wei-Hung Weng , Alexander Daryin , Tao Tu , Petar Sirkovic , Artiom Myaskovsky , Grzegorz Glowaty , Felix Weissenberger , Alessio Orlandi , Dan Popovici , Anil Palepu , Keran Rong , Ryutaro Tanno , Khaled Saab , Fan Zhang , Jacob Blum , Andrew Carroll , Kavita Kulkarni , Nenad Tomasev , Dina Zverinski , Ivor Rendulic , Elahe Vedadi , Florian Hasler , Luka Rimanic , Marina Boia , Ivan Budiselic , Ben Feinstein , Mathias Bellaiche , Tom Sheffer , Jan Freyberg , Jeremy Ratcliff , Ottavia Bertolli , Katherine Chou , Avinatan Hassidim , Burak Gokturk , Amin Vahdat , Yuan Guan , Vikram Dhillon , Eeshit Dhaval Vaishnav , Byron Lee , Tiago R D Costa , José R Penadés , Gary Peltz , Yossi Matias , James Manyika , Demis Hassabis , Yunhan Xu , Pushmeet Kohli , Annalisa Pawlosky , Alan Karthikesalingam , Vivek Natarajan\nView a PDF of the paper titled Accelerating scientific discovery with Co-Scientist, by Juraj Gottweis and 50 other authors\nView PDF\nAbstract: Scientific discovery is driven by scientists generating novel hypotheses for complex problems that undergo rigorous experimental validation. To augment this process, we introduce Co-Scientist, a multi-agent AI system built on Gemini for structured scientific thinking and hypothesis generation. Co-Scientist aims to help scientists discover new original knowledge. Conditioned on their research objectives and prior scientific evidence, it formulates demonstrably novel research hypotheses for experimental verification. The system's design involves agents continuously generating, critiquing and refining hypotheses accelerated by scaling test-time compute. Key contributions include: (1) a multi-agent architecture with an asynchronous task execution framework for flexible compute scaling; (2) a tournament evolution process for self-improving hypotheses generation. Automated evaluations show continued benefits of test-time compute scaling, improving hypothesis quality over time. While general purpose, we focus the validation in three biomedical applications: drug repurposing, novel target discovery, and explaining mechanisms of anti-microbial resistance. Specifically, Co-Scientist helped identify new drug repurposing candidates and synergistic combination therapies for acute myeloid leukemia, which were validated through in vitro experiments. These real-world validations demonstrate the potential of Co-Scientist to accelerate scientific discovery and usher in an era of AI empowered scientists.\nComments:\n157 pages in total (main 42 pages, supplementary information 115 pages), 4 main figures, 1 main table, 6 extended data figures, 2 extended data tables, 9 supplementary figures, 4 supplementary tables, 37 main references, 117 supplementary references. Nature (2026)\nSubjects:\nArtificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG); Physics and Society (physics.soc-ph); Other Quantitative Biology (q-bio.OT)\nCite as:\narXiv:2502.18864 [cs.AI]\n(or\narXiv:2502.18864v2 [cs.AI] for this version)\nhttps://doi.org/10.48550/arXiv.2502.18864\nFocus to learn more\narXiv-issued DOI via DataCite\nRelated DOI :\nhttps://doi.org/10.1038/s41586-026-10644-y\nFocus to learn more\nDOI(s) linking to related resources\nSubmission history\nFrom: Wei-Hung Weng [ view email ] [v1]\nWed, 26 Feb 2025 06:17:13 UTC (1,807 KB)\n[v2]\nMon, 29 Jun 2026 16:12:47 UTC (5,747 KB)\nFull-text links:\nAccess Paper:\nView a PDF of the paper titled Accelerating scientific discovery with Co-Scientist, by Juraj Gottweis and 50 other authors\nView PDF\nview license\nCurrent browse conte","chars":4000,"total_chars":6289,"offset":0,"truncated":true,"next_offset":4000}