{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T18:51:23Z","timestamp":1793386283840,"version":"4.5.0"},"reference-count":74,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    The automation of chemical research through self-driving laboratories (SDLs) promises to accelerate scientific discovery, yet the reliability and granular performance of the underlying AI agents remain critical, under-examined challenges. In this work, we introduce AutoLabs, a self-correcting, multi-agent architecture designed to autonomously translate natural-language instructions into executable protocols for a high-throughput liquid handler. The system engages users in dialogue, decomposes experimental goals into discrete tasks for specialized agents, performs tool-assisted stoichiometric calculations, and iteratively self-corrects its output before generating a hardware-ready file. We present a comprehensive evaluation framework featuring five benchmark experiments of increasing complexity, from simple sample preparation to multi-plate timed syntheses. Through a systematic ablation study of 20 agent configurations, we assess the impact of reasoning capacity, architectural design (single- vs. multi-agent), tool use, and self-correction mechanisms. Our results demonstrate that agent reasoning capacity is the most critical factor for success, reducing quantitative errors in chemical amounts (nRMSE) by over 85% in complex tasks. When combined with a multi-agent architecture and iterative self-correction, AutoLabs approaches expert-authored reference procedures on the benchmark (F1-score &gt; 0.89) on challenging multi-plate syntheses. These findings establish a clear blueprint for developing robust and trustworthy AI partners for autonomous laboratories, highlighting the synergistic effects of modular design, advanced reasoning, and self-correction to ensure both performance and reliability in high-stakes scientific applications. Code:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/pnnl\/autolabs\" ext-link-type=\"uri\">https:\/\/github.com\/pnnl\/autolabs<\/jats:ext-link>\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-45593-z","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T09:03:38Z","timestamp":1782378218000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["AutoLabs: cognitive multi-agent systems with self-correction for autonomous chemical experimentation"],"prefix":"10.1038","volume":"16","author":[{"given":"Gihan","family":"Panapitiya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emily","family":"Saldanha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heather","family":"Job","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivia","family":"Hess","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"45593_CR1","unstructured":"OpenAI et al. Gpt-4 technical report (2024). arXiv:2303.08774."},{"key":"45593_CR2","unstructured":"DeepSeek-AI et al. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning (2025). arXiv:2501.12948."},{"key":"45593_CR3","doi-asserted-by":"crossref","unstructured":"Shinn, N. et al. Reflexion: Language Agents with Verbal Reinforcement Learning (2023). ArXiv:2303.11366 [cs].","DOI":"10.52202\/075280-0377"},{"key":"45593_CR4","unstructured":"Wang, X. et al. Executable code actions elicit better llm agents (2024). arXiv:2402.01030."},{"key":"45593_CR5","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A. & Klimov, O. Proximal policy optimization algorithms (2017). arXiv:1707.06347."},{"key":"45593_CR6","unstructured":"Rafailov, R. et al. Direct preference optimization: Your language model is secretly a reward model (2024). arXiv:2305.18290."},{"key":"45593_CR7","unstructured":"Xu, C. et al. Wizardlm: Empowering large pre-trained language models to follow complex instructions (2025). arXiv:2304.12244."},{"key":"45593_CR8","unstructured":"OpenAI et al. Competitive programming with large reasoning models (2025). arXiv:2502.06807."},{"key":"45593_CR9","doi-asserted-by":"crossref","unstructured":"Burger, B. et al. A mobile robotic chemist. Nature 583, 237\u2013241 (2020). https:\/\/www.nature.com\/articles\/s41586-020-2442-2. Publisher: Nature Publishing Group.","DOI":"10.1038\/s41586-020-2442-2"},{"key":"45593_CR10","doi-asserted-by":"crossref","unstructured":"Zhao, H. et al. A robotic platform for the synthesis of colloidal nanocrystals. Nature Synthesis 2, 505\u2013514 (2023). https:\/\/www.nature.com\/articles\/s44160-023-00250-5. Publisher: Nature Publishing Group.","DOI":"10.1038\/s44160-023-00250-5"},{"key":"45593_CR11","doi-asserted-by":"publisher","first-page":"1311","DOI":"10.1038\/s41557-022-01016-w","volume":"14","author":"JS Manzano","year":"2022","unstructured":"Manzano, J. S. et al. An autonomous portable platform for universal chemical synthesis. Nat. Chem. 14, 1311\u20131318 (2022).","journal-title":"Nat. Chem."},{"key":"45593_CR12","doi-asserted-by":"publisher","DOI":"10.1126\/science.adj1817","volume":"383","author":"A Slattery","year":"2024","unstructured":"Slattery, A. et al. Automated self-optimization, intensification, and scale-up of photocatalysis in flow. Science 383, eadj1817 (2024).","journal-title":"Science"},{"key":"45593_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, Y. et al. Autonomous biomimetic solid dispensing using a dual-arm robotic manipulator. Digital Discovery 2, 1733\u20131744 (2023). https:\/\/pubs.rsc.org\/en\/content\/articlelanding\/2023\/dd\/d3dd00075c. Publisher: RSC.","DOI":"10.1039\/D3DD00075C"},{"key":"45593_CR14","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-05271-9","volume":"9","author":"RL Greenaway","year":"2018","unstructured":"Greenaway, R. L. et al. High-throughput discovery of organic cages and catenanes using computational screening fused with robotic synthesis. Nat. Commun. 9, 2849. https:\/\/doi.org\/10.1038\/s41467-018-05271-9 (2018).","journal-title":"Nat. Commun."},{"key":"45593_CR15","doi-asserted-by":"crossref","unstructured":"Lunt, A.\u00a0M. et al. Modular, multi-robot integration of laboratories: an autonomous workflow for solid-state chemistry. Chemical Science 15, 2456\u20132463 (2024). https:\/\/pubs.rsc.org\/en\/content\/articlelanding\/2024\/sc\/d3sc06206f. Publisher: The Royal Society of Chemistry.","DOI":"10.1039\/D3SC06206F"},{"key":"45593_CR16","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1126\/science.abc2986","volume":"370","author":"SHM Mehr","year":"2020","unstructured":"Mehr, S. H. M., Craven, M., Leonov, A. I., Keenan, G. & Cronin, L. A universal system for digitization and automatic execution of the chemical synthesis literature. Science 370, 101\u2013108. https:\/\/doi.org\/10.1126\/science.abc2986 (2020).","journal-title":"Science"},{"key":"45593_CR17","doi-asserted-by":"publisher","first-page":"1221","DOI":"10.1126\/science.aaa5414","volume":"347","author":"J Li","year":"2015","unstructured":"Li, J. et al. Synthesis of many different types of organic small molecules using one automated process. Science 347, 1221\u20131226. https:\/\/doi.org\/10.1126\/science.aaa5414 (2015).","journal-title":"Science"},{"key":"45593_CR18","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1038\/s41586-018-0307-8","volume":"559","author":"JM Granda","year":"2018","unstructured":"Granda, J. M., Donina, L., Dragone, V., Long, D.-L. & Cronin, L. Controlling an organic synthesis robot with machine learning to search for new reactivity. Nature 559, 377\u2013381. https:\/\/doi.org\/10.1038\/s41586-018-0307-8 (2018).","journal-title":"Nature"},{"key":"45593_CR19","doi-asserted-by":"publisher","first-page":"28952","DOI":"10.1021\/jacs.4c09553","volume":"146","author":"D He","year":"2024","unstructured":"He, D. et al. Algorithm-driven robotic discovery of polyoxometalate-scaffolding metal-organic frameworks. J. Am. Chem. Soc. 146, 28952\u201328960. https:\/\/doi.org\/10.1021\/jacs.4c09553 (2024).","journal-title":"J. Am. Chem. Soc."},{"key":"45593_CR20","doi-asserted-by":"crossref","unstructured":"Szymanski, N.\u00a0J. et al. An autonomous laboratory for the accelerated synthesis of novel materials. Nature 624, 86\u201391 (2023). https:\/\/www.nature.com\/articles\/s41586-023-06734-w. Publisher: Nature Publishing Group.","DOI":"10.1038\/s41586-023-06734-w"},{"key":"45593_CR21","doi-asserted-by":"crossref","unstructured":"Zhu, Q. et al. Automated synthesis of oxygen-producing catalysts from Martian meteorites by a robotic AI chemist. Nature Synthesis 3, 319\u2013328 (2024). https:\/\/www.nature.com\/articles\/s44160-023-00424-1. Publisher: Nature Publishing Group.","DOI":"10.1038\/s44160-023-00424-1"},{"key":"45593_CR22","unstructured":"Gridach, M., Nanavati, J., Abidine, K. Z.\u00a0E., Mendes, L. & Mack, C. Agentic ai for scientific discovery: A survey of progress, challenges, and future directions (2025). arXiv:2503.08979."},{"key":"45593_CR23","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1038\/s41586-023-06792-0","volume":"624","author":"DA Boiko","year":"2023","unstructured":"Boiko, D. A., MacKnight, R., Kline, B. & Gomes, G. Autonomous chemical research with large language models. Nature 624, 570\u2013578 (2023).","journal-title":"Nature"},{"key":"45593_CR24","unstructured":"Boiko, D.\u00a0A., MacKnight, R. & Gomes, G. Emergent autonomous scientific research capabilities of large language models (2023). arXiv:2304.05332."},{"key":"45593_CR25","doi-asserted-by":"crossref","unstructured":"Campbell, Q., Cox, S., Medina, J., Watterson, B. & White, A.\u00a0D. Mdcrow: Automating molecular dynamics workflows with large language models (2025). arXiv:2502.09565.","DOI":"10.1088\/2632-2153\/ae4b07"},{"key":"45593_CR26","doi-asserted-by":"publisher","first-page":"12534","DOI":"10.1021\/jacs.4c17738","volume":"147","author":"T Song","year":"2025","unstructured":"Song, T. et al. A multiagent-driven robotic AI chemist enabling autonomous chemical research on demand. J. Am. Chem. Soc. 147, 12534\u201312545 (2025).","journal-title":"J. Am. Chem. Soc."},{"key":"45593_CR27","doi-asserted-by":"publisher","first-page":"55682","DOI":"10.1109\/ACCESS.2024.3387941","volume":"12","author":"SH Vemprala","year":"2024","unstructured":"Vemprala, S. H., Bonatti, R., Bucker, A. & Kapoor, A. ChatGPT for robotics: Design principles and model abilities. IEEE Access 12, 55682\u201355696 (2024).","journal-title":"IEEE Access"},{"key":"45593_CR28","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1038\/s44286-024-00033-5","volume":"1","author":"JA Bennett","year":"2024","unstructured":"Bennett, J. A. et al. Autonomous reaction Pareto-front mapping with a self-driving catalysis laboratory. Nat. Chem. Eng. 1, 240\u2013250 (2024).","journal-title":"Nat. Chem. Eng."},{"key":"45593_CR29","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-59231-1","volume":"16","author":"RB Canty","year":"2025","unstructured":"Canty, R. B. et al. Science acceleration and accessibility with self-driving labs. Nat. Commun. 16, 3856 (2025).","journal-title":"Nat. Commun."},{"key":"45593_CR30","doi-asserted-by":"publisher","first-page":"9633","DOI":"10.1021\/acs.chemrev.4c00055","volume":"124","author":"G Tom","year":"2024","unstructured":"Tom, G. et al. Self-driving laboratories for chemistry and materials science. Chem. Rev. 124, 9633\u20139732. https:\/\/doi.org\/10.1021\/acs.chemrev.4c00055 (2024).","journal-title":"Chem. Rev."},{"key":"45593_CR31","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aaz8867","volume":"6","author":"BP MacLeod","year":"2020","unstructured":"MacLeod, B. P. et al. Self-driving laboratory for accelerated discovery of thin-film materials. Sci. Adv. 6, eaaz8867. https:\/\/doi.org\/10.1126\/sciadv.aaz8867 (2020).","journal-title":"Sci. Adv."},{"key":"45593_CR32","doi-asserted-by":"crossref","unstructured":"Yang, Z. et al. Large language models for automated open-domain scientific hypotheses discovery (2024). arXiv:2309.02726.","DOI":"10.18653\/v1\/2024.findings-acl.804"},{"key":"45593_CR33","unstructured":"Zhou, Z. et al. From hypothesis to publication: A comprehensive survey of ai-driven research support systems (2025). arXiv:2503.01424."},{"key":"45593_CR34","unstructured":"Team, I. et al. Internagent: When agent becomes the scientist \u2013 building closed-loop system from hypothesis to verification (2025). arXiv:2505.16938."},{"key":"45593_CR35","unstructured":"Takagi, S., Yamauchi, R. & Kumagai, W. Towards autonomous hypothesis verification via language models with minimal guidance. arXiv 2311.09706 (2023)."},{"key":"45593_CR36","doi-asserted-by":"crossref","unstructured":"Rabby, G., Muhammed, D., Mitra, P. & Auer, S. Iterative hypothesis generation for scientific discovery with Monte Carlo Nash Equilibrium self-refining trees. arXiv 2503.19309 (2025).","DOI":"10.1016\/j.ins.2026.123576"},{"key":"45593_CR37","doi-asserted-by":"crossref","unstructured":"Newman, B. et al. Arxivdigestables: Synthesizing scientific literature into tables using language models (2024). arXiv:2410.22360.","DOI":"10.18653\/v1\/2024.emnlp-main.538"},{"key":"45593_CR38","doi-asserted-by":"crossref","unstructured":"Chen, K. et al. Chemminer: A large language model agent system for chemical literature data mining (2025). arXiv:2402.12993.","DOI":"10.1109\/ICCVW69036.2025.00787"},{"key":"45593_CR39","doi-asserted-by":"crossref","unstructured":"Song, Y. et al. Trial and error: Exploration-based trajectory optimization for llm agents (2024). arXiv:2403.02502.","DOI":"10.18653\/v1\/2024.acl-long.409"},{"key":"45593_CR40","unstructured":"Chen, K. et al. Chemist-x: Large language model-empowered agent for reaction condition recommendation in chemical synthesis (2025). arXiv:2311.10776."},{"key":"45593_CR41","doi-asserted-by":"crossref","unstructured":"Darvish, K. et al. Organa: A robotic assistant for automated chemistry experimentation and characterization. Matter 8, 101897 (2025). https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2590238524005423.","DOI":"10.1016\/j.matt.2024.10.015"},{"key":"45593_CR42","doi-asserted-by":"crossref","unstructured":"Dai, T. et al. Autonomous mobile robots for exploratory synthetic chemistry. Nature 635, 890\u2013897 (2024). https:\/\/www.nature.com\/articles\/s41586-024-08173-7. Publisher: Nature Publishing Group.","DOI":"10.1038\/s41586-024-08173-7"},{"key":"45593_CR43","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-37139-y","volume":"14","author":"AA Volk","year":"2023","unstructured":"Volk, A. A. et al. AlphaFlow: Autonomous discovery and optimization of multi-step chemistry using a self-driven fluidic lab guided by reinforcement learning. Nat. Commun. 14, 1403 (2023).","journal-title":"Nat. Commun."},{"key":"45593_CR44","doi-asserted-by":"publisher","DOI":"10.1126\/science.adi1407","volume":"382","author":"BA Koscher","year":"2023","unstructured":"Koscher, B. A. et al. Autonomous, multiproperty-driven molecular discovery: From predictions to measurements and back. Science 382, eadi1407. https:\/\/doi.org\/10.1126\/science.adi1407 (2023).","journal-title":"Science"},{"key":"45593_CR45","unstructured":"Burge, R. & Reynaud, F. Comparison of manual versus automated protein formulation development workflow on a Big Kahuna ."},{"key":"45593_CR46","unstructured":"LangChain. Langgraph. https:\/\/github.com\/langchain-ai\/langgraph (2024). Part of the LangChain framework."},{"key":"45593_CR47","doi-asserted-by":"crossref","unstructured":"Ghafarollahi, A. & Buehler, M.\u00a0J. Sciagents: Automating scientific discovery through multi-agent intelligent graph reasoning (2024). arXiv:2409.05556.","DOI":"10.1002\/adma.202413523"},{"key":"45593_CR48","doi-asserted-by":"crossref","unstructured":"Sapkota, R., Roumeliotis, K.\u00a0I. & Karkee, M. Ai agents vs. agentic ai: A conceptual taxonomy, applications and challenges (2025). arXiv:2505.10468.","DOI":"10.70777\/si.v2i3.15161"},{"key":"45593_CR49","unstructured":"Packer, C. et al. Memgpt: Towards llms as operating systems (2024). arXiv:2310.08560."},{"key":"45593_CR50","unstructured":"Yuan, S. et al. Easytool: Enhancing llm-based agents with concise tool instruction (2024). arXiv:2401.06201."},{"key":"45593_CR51","doi-asserted-by":"crossref","unstructured":"Yu, B. et al. Chemtoolagent: The impact of tools on language agents for chemistry problem solving (2025). arXiv:2411.07228.","DOI":"10.18653\/v1\/2025.findings-naacl.424"},{"key":"45593_CR52","doi-asserted-by":"crossref","unstructured":"Yang, R. et al. Gpt4tools: Teaching large language model to use tools via self-instruction (2023). arXiv:2305.18752.","DOI":"10.52202\/075280-3149"},{"key":"45593_CR53","unstructured":"Wu, M. et al. Chematagent: Enhancing llms for chemistry and materials science through tree-search based tool learning (2025). arXiv:2506.07551."},{"key":"45593_CR54","doi-asserted-by":"crossref","unstructured":"Zhu, Y. et al. Knowagent: Knowledge-augmented planning for llm-based agents (2025). arXiv:2403.03101.","DOI":"10.18653\/v1\/2025.findings-naacl.205"},{"key":"45593_CR55","unstructured":"Zhu, Y. et al. Healthflow: A self-evolving ai agent with meta planning for autonomous healthcare research (2025). arXiv:2508.02621."},{"key":"45593_CR56","unstructured":"Zhou, L. et al. Toward greater autonomy in materials discovery agents: Unifying planning, physics, and scientists (2025). arXiv:2506.05616."},{"key":"45593_CR57","doi-asserted-by":"crossref","unstructured":"Rivera, C. et al. Conceptagent: Llm-driven precondition grounding and tree search for robust task planning and execution (2024). arXiv:2410.06108.","DOI":"10.1109\/ICRA55743.2025.11128414"},{"key":"45593_CR58","unstructured":"Zhou, Y. et al. Scientists\u2019 first exam: Probing cognitive abilities of mllm via perception, understanding, and reasoning (2025). arXiv:2506.10521."},{"key":"45593_CR59","unstructured":"Yao, S. et al. React: Synergizing reasoning and acting in language models (2023). arXiv:2210.03629."},{"key":"45593_CR60","unstructured":"Xu, Y., Kimlee, H., Xiao, Y. & Luo, D. Advancing ai-scientist understanding: Multi-agent llms with interpretable physics reasoning (2025). arXiv:2504.01911."},{"key":"45593_CR61","unstructured":"Wei, J. et al. Alignrag: Leveraging critique learning for evidence-sensitive retrieval-augmented reasoning (2025). arXiv:2504.14858."},{"key":"45593_CR62","doi-asserted-by":"crossref","unstructured":"Wei, J. et al. Chain-of-thought prompting elicits reasoning in large language models (2023). arXiv:2201.11903.","DOI":"10.52202\/068431-1800"},{"key":"45593_CR63","unstructured":"Lu, C. et al. The ai scientist: Towards fully automated open-ended scientific discovery (2024). arXiv:2408.06292."},{"key":"45593_CR64","doi-asserted-by":"crossref","unstructured":"Feng, G. et al. Oh, A. et al. (eds) Towards revealing the mystery behind chain of thought: A theoretical perspective. (eds Oh, A. et al.) Advances in Neural Information Processing Systems, Vol.\u00a036, 70757\u201370798 (Curran Associates, Inc., 2023). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/dfc310e81992d2e4cedc09ac47eff13e-Paper-Conference.pdf.","DOI":"10.52202\/075280-3100"},{"key":"45593_CR65","unstructured":"Sun, J. et al. A survey of reasoning with foundation models (2024). arXiv:2312.11562."},{"key":"45593_CR66","unstructured":"Schulhoff, S. et al. The prompt report: A systematic survey of prompt engineering techniques (2025). arXiv:2406.06608."},{"key":"45593_CR67","unstructured":"Suzgun, M. & Kalai, A.\u00a0T. Meta-prompting: Enhancing language models with task-agnostic scaffolding (2024). arXiv:2401.12954."},{"key":"45593_CR68","doi-asserted-by":"publisher","first-page":"25985","DOI":"10.1609\/aaai.v39i24.34793","volume":"39","author":"Y Zhang","year":"2025","unstructured":"Zhang, Y., Wang, X., Wu, L. & Wang, J. Enhancing chain of thought prompting in large language models via reasoning patterns. Proc. AAAI Conf. Artif. Intell. 39, 25985\u201325993. https:\/\/doi.org\/10.1609\/aaai.v39i24.34793 (2025).","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"45593_CR69","doi-asserted-by":"crossref","unstructured":"Jiang, H., Wu, Q., Lin, C.-Y., Yang, Y. & Qiu, L. Llmlingua: Compressing prompts for accelerated inference of large language models (2023). arXiv:2310.05736.","DOI":"10.18653\/v1\/2023.emnlp-main.825"},{"key":"45593_CR70","doi-asserted-by":"publisher","first-page":"1057","DOI":"10.1007\/s10514-023-10136-2","volume":"47","author":"N Yoshikawa","year":"2023","unstructured":"Yoshikawa, N. et al. Large language models for chemistry robotics. Auton. Robots 47, 1057\u20131086 (2023).","journal-title":"Auton. Robots"},{"key":"45593_CR71","first-page":"707","volume":"10","author":"VI Levenshtein","year":"1966","unstructured":"Levenshtein, V. I. Binary codes capable of correcting deletions, insertions and reversals. Sov. Phys. Dokl. 10, 707 (1966).","journal-title":"Sov. Phys. Dokl."},{"key":"45593_CR72","unstructured":"Fundamental Algorithms for Scientific Computing in Python. Virtanen, P. et al. SciPy 1.0. Nature Methods 17, 261\u2013272 (2020)."},{"key":"45593_CR73","unstructured":"Gao, Y. et al. Retrieval-augmented generation for large language models: A survey (2024). arXiv:2312.10997."},{"key":"45593_CR74","doi-asserted-by":"crossref","unstructured":"Fan, W. et al. A survey on rag meeting llms: Towards retrieval-augmented large language models (2024). arXiv:2405.06211.","DOI":"10.1145\/3637528.3671470"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-45593-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-45593-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-45593-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T09:05:26Z","timestamp":1782378326000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-45593-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":74,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["45593"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-45593-z","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,25]]},"assertion":[{"value":"20 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}],"article-number":"19554"}}