DORA AI Scientist: Multi-agent Virtual Research Team for Scientific Exploration Discovery and Automated Report Generation
Open accessAbstract
Abstract Modern goal-oriented scientific research process involves hierarchical teams of researchers of diverse backgrounds performing generalist and domain-specific tasks. Many of these tasks include hypothesis generation, literature review, data collection, cleanup, processing and analysis, experimental design, virtual and physical experiments, research report and academic paper writing, reference management, bibliography and quality control. Most of these tasks can be performed automatically or in a co-pilot mode by the generative reinforcement learning systems. In this paper, we introduce a versatile multi-agent scientific exploration and draft outline research assistant (DORA), which provides multiple templates and workflows for automated or semi-automated research studies and report generation. Under user guidance, it employs hierarchical teams of AI agents based on the plug-and-play generalist and domain-specific large language models (LLMs) exploiting a variety of specialized research tools and open data repositories and generates high-quality research outputs publication drafts with maximally-accurate references. DORA is designed to minimize the time and effort required for manuscript preparation, thereby enabling researchers to devote more attention to high-value discovery tasks. The system is constantly evolving with user feedback with regular feature and resource updates. The platform is available at https://dora.insilico.com .
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
Cites
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604 · see citing works
A survey on large language model based autonomous agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2024) · Frontiers of Computer Science · doi:10.1007/s11704-024-40231-1 · Cited by 1,941 · see citing works
Gemini: A Family of Highly Capable Multimodal Models
Gemini Team, Anil, R., Borgeaud, S., Alayrac, J.-B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A. M., Hauth, A., Millican, K., et al. (2023) · arXiv · doi:10.48550/arxiv.2312.11805 · Cited by 990 · see citing works
A large-scale comparison of human-written versus ChatGPT-generated essays
Herbold, S., Hautli-Janisz, A., Heuer, U., Kikteva, Z., & Trautsch, A. (2023) · Scientific Reports · doi:10.1038/s41598-023-45644-9 · Cited by 338 · see citing works
Empowering biomedical discovery with AI agents
Gao, S., Fang, A., Huang, Y., Giunchiglia, V., Noori, A., Schwarz, J. R., Ektefaie, Y., Kondic, J., & Zitnik, M. (2024) · Cell · doi:10.1016/j.cell.2024.09.022 · Cited by 315 · see citing works
The role of ChatGPT in scientific communication: writing better scientific review articles.
(2023) · PubMed Central · Cited by 289 · see citing works
Exploring Large Language Model‐Based Intelligent Agents: Definitions, Methods, and Prospects
Cheng, Y.-H., Zhang, C., Zhang, Z.-W., Meng, X.-R., Hong, S.-R., Li, W.-H., Wang, Z., Wang, Z.-K., Yin, F., Zhao, J.-H., et al. (2024) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.70111 · Cited by 241 · see citing works
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Zhang, C., Wang, J., Wang, Z., Yau, S. K. S., Lin, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.00352 · Cited by 214 · see citing works
A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions
Wu, J., Yang, S., Zhan, R., Yuan, Y., Wong, D. F., & Chao, L. S. (2023) · arXiv · doi:10.48550/arxiv.2310.14724 · Cited by 212 · see citing works
A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions
Wu, J., Yang, S., Zhan, R., Yuan, Y., Chao, L. S., & Wong, D. F. (2025) · Computational Linguistics · doi:10.1162/coli_a_00549 · Cited by 212 · see citing works
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
Wu, Q., Bansal, G., Zhang, J., Wu, Y., Li, B., Zhu, E., Jiang, L., Zhang, X., Zhang, S., Liu, J., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.08155 · Cited by 193 · see citing works
PandaOmics: An AI-Driven Platform for Therapeutic Target and Biomarker Discovery
Kamya, P. R. N., Ozerov, I. V., Pun, F. W., Tretina, K., Fokina, T., Chen, S., Naumov, V., Long, X., Lin, S., Korzinkin, M., et al. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c01619 · Cited by 156 · see citing works
Self-citationIbrahim, H., Liu, F., Asim, R., Battu, B., Benabderrahmane, S., Alhafni, B., Adnan, W., Alhanai, T., AlShebli, B., Baghdadi, R., et al. (2023) · Scientific Reports · doi:10.1038/s41598-023-38964-3 · Cited by 154 · see citing works
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
Lu, C., Lu, C., Lange, R. T., Foerster, J., Clune, J., & Ha, D. (2024) · arXiv · doi:10.48550/arxiv.2408.06292 · Cited by 118 · see citing works
Leveraging Large Language Models for NLG Evaluation: Advances and Challenges
Li, Z. K., Xu, X., Shen, T., Xu, C., Gu, J.-C., Lai, Y., Tao, C., & Ma, S. (2024) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2024.emnlp-main.896 · Cited by 63 · see citing works
Main barriers and possible enablers of academicians while publishing
Aydin, A., Yürük, S. E., Reisoğlu, İ., & Goktas, Y. (2023) · Scientometrics · doi:10.1007/s11192-022-04528-x · Cited by 55 · see citing works
Use of Artificial Intelligence Tools for Research by Medical Students: A Narrative Review
Jhajj, K. S., Jindal, P., & Kaur, K. (2024) · Cureus · doi:10.7759/cureus.55367 · Cited by 35 · see citing works
Balakumar, P., Inamdar, M. N., & Jagadeesh, G. (2013) · Journal of Pharmacology and Pharmacotherapeutics · doi:10.4103/0976-500x.110895 · Cited by 29 · see citing works
Benchmarking LLM powered Chatbots: Methods and Metrics
Banerjee, D., Singh, P., Avadhanam, A., & Srivastava, S. (2023) · arXiv · doi:10.48550/arxiv.2308.04624 · Cited by 18 · see citing works
Galkin, F., Naumov, V., Pushkov, S., Sidorenko, D., Urban, A. S., Zagirova, D., Alawi, K. M., Aliper, A., Gumerov, R., Kalashnikov, A., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.07.25.605062 · Cited by 18 · see citing works
Self-citationPlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and DetectionPreprint
Lee, J., Agrawal, T., Uchendu, A., Le, T., Chen, J.-H., & Lee, D. (2024) · North American Chapter of the Association for Computational Linguistics · doi:10.48550/arxiv.2406.16288 · Cited by 13 · see citing works
Leveraging Multi-AI Agents for Cross-Domain Knowledge DiscoveryPreprint
Aryal, S., Do, T., Heyojoo, B., Chataut, S., Gurung, B. D. S., Gadhamshetty, V. R., & Gnimpiéba, E. Z. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.08511 · Cited by 8 · see citing works
Remmel, H. L., Hammer, S. S., Singh, H., Shneyderman, A., Veviorskiy, A., Alawi, K. M., Korzinkin, M., Zhavoronkov, A. A., & Quay, S. C. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.10.02.616224 · Cited by 6 · see citing works
Self-citationAI-driven toolset for IPF and aging research associates lung fibrosis with accelerated aging
Galkin, F., Chen, S., Aliper, A. M., Zhavoronkov, A. A., & Ren, F. (2025) · Aging · doi:10.18632/aging.206295 · Cited by 4 · see citing works
Self-citationCOSMIC: Molecular Conformation Space Modeling in Internal Coordinates with an Adversarial Framework
Kuznetsov, M., Ryabov, F., Schutski, R., Shayakhmetov, R., Lin, Y., Aliper, A., & Polykovskiy, D. A. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c00989 · Cited by 3 · see citing works
Self-citationVeviorskiy, A., Mkrtchyan, G. V., Osipov, A. N., Izumchenko, E., Ozerov, I. V., Aliper, A., Zhavoronkov, A. A., & Scheibye‐Knudsen, M. (2025) · Aging · doi:10.18632/aging.206212 · Cited by 3 · see citing works
Self-citationVeviorskiy, A., Mkrtchyan, G. V., Osipov, A. N., et al. (2024) · medRxiv · doi:10.1101/2024.07.04.24309952 · Cited by 2 · see citing works
Designing a multi-serotype Dengue virus vaccine: an in silico approach to broad-spectrum immunityPreprint
Singh, A., Glushchenko, O. E., Ustiugova, A. S., Alawi, K. M., Korzinkin, M., Zhavoronkov, A. A., & Castiglione, F. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.12.02.626364 · Cited by 2 · see citing works
Self-citationAI-Driven Toolset for IPF and Aging Research Associates Lung Fibrosis with Accelerated AgingPreprint
Galkin, F., Chen, S., Aliper, A. M., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.01.09.632065 · Cited by 1 · see citing works
Self-citationKAOS: Large Model Multi-agent Operating System
Zhuo, Z., Li, R., Liu, K., Zou, H., Li, K., Yu, J., Sun, T., & Wu, Q. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-1809-5_27 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
AlphaEvolve: A coding agent for scientific and algorithmic discovery
Novikov, A., Vũ, N., Eisenberger, M., Dupont, E., Huang, P.-S., Wagner, A. Z., Shirobokov, S., Kozlovskii, B., Ruiz, F. J. R., Mehrabian, A., et al. (2025) · arXiv · doi:10.48550/arxiv.2506.13131 · Cited by 15 · see citing works
“Other works use LLMs to optimize experimental planning and design [7, 10, 43, 75] or experiment execution and workflow [28, 62, 82, 105, 116].”
OriGene: A Self-Evolving Virtual Disease Biologist Automating Therapeutic Target DiscoveryPreprint
Zhang, Z.-Y., Qiu, Z.-J., Wu, Y.-C., Li, S., Wang, D.-Y., Liu, Y., Zhou, Z., Hu, Y.-S., Chen, Y., An, D., et al. (2026) · bioRxiv · doi:10.1101/2025.06.03.657658 · Cited by 33 · see citing works
From Prompt to Drug: Toward Pharmaceutical Superintelligence
Zhavoronkov, A. A., Gennert, D. G., & Shi, J. (2026) · ACS Central Science · doi:10.1021/acscentsci.5c01473 · Cited by 12 · see citing works
Self-citationGeneral-Purpose Models for the Chemical Sciences: LLMs and Beyond
Alampara, N., Aneesh, A., Ríos-García, M., Mirza, A., Schilling-Wilhelmi, M., Aghajani, A. A., Sun, M., Prastalo, G., & Jablonka, K. M. (2026) · Chemical Reviews · doi:10.1021/acs.chemrev.5c00583 · Cited by 12 · see citing works
El agente cuántico: automating quantum simulations
Gustín, I., Calderón, L., Pérez-Sánchez, J. B., Crebolder, C., Gonthier, J. F., Vakili, M. G., Nakamura, Y., Panicker, K., Ramprasad, M., Yin, A., et al. (2026) · Reports on Progress in Physics · doi:10.1088/1361-6633/ae8933 · Cited by 5 · see citing works
Self-citationA Review of Multi-Agent AI Systems for Biological and Clinical Data Analysis
Spieser, J., Balapour, A., Meller, J., Patra, K. C., & Shamsaei, B. (2026) · Methods and Protocols · doi:10.3390/mps9020033 · Cited by 1 · see citing works
“Future systems must therefore utilize dynamic orchestration to selectively deploy agentic teams based on task complexity, ensuring that resource-intensive multi-agent deliberation is reserved for high-stakes clinical scenarios where the cost of error exceeds the marginal cost of compute [38,56].”
Practical Use of Advanced AI Frameworks on Real-Life Scientific Problems: Three Case StudiesPreprint
Gulluoglu, H. S. A., Baby, J., Bagul, K. M., Basangari, B. R., Bathini, S. A., Chalamalla, N. K. R., Dcunha, J., Gupta, O., Huang, L., Jiang, X., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.23.734132 · Cited by 2 · see citing works
- Authors
- Naumov, V., Zagirova, D., Lin, S., Xie, Y., Gou, W., Urban, A., Tikhonova, N., Alawi, K., Durymanov, M., Galkin, F., Chen, S., Sidorenko, D., Korzinkin, M., Scheibye-Knudsen, M., Aspuru-Guzik, A., Izumchenko, E., Gennert, D., Pun, F. W., Zhang, M., Kamya, P., Aliper, A., Ren, F., & Zhavoronkov, A.
- Affiliations
- Insilico Medicine AI Limited, Abu Dhabi, UAE
- Hong Kong Science and Technology Parks Corporation (HK)
- Insilico Medicine Shanghai Ltd., Shanghai, China
- Center for Healthy Aging, Department of Cellular and Molecular Medicine, University of Copenhagen, Denmark
- University of Toronto, Department of Chemistry and Department of Computer Science, Toronto, Canada
- University of Chicago (US)
- Insilico Medicine (United States) (US)
- Insilico Medicine Canada Inc, Montreal, Quebec, Canada
- Corresponding author
- Zhavoronkov, Alex
- ORCID
- Venue
- bioRxiv (Cold Spring Harbor Laboratory)
- Publisher
- openRxiv
- Published
- 2025-03-07
- OpenAlex
- W4408224138
- Cited by
- 5
- References
- 28
- Citations by year
- 2026: 4 · 2025: 1
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Licence
- Locations
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- Topics
- Social Sciences › Arts and Humanities › History and Philosophy of Science › Academic Writing and Publishing
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Social Sciences › Decision Sciences › Information Systems and Management › Scientific Computing and Data Management
- Keywords
- multi-agent systems, AI research assistant, automated reporting, scientific exploration, large language models, generative AI, citation management, hypothesis generation, research workflow automation, DORA
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
