基于多模态 LLM 智能体的假设驱动自主材料合成

Condensed Matter > Materials Science arXiv:2609.18598 (cond-mat) [Submitted on 16 Sep 2026] Title:Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents Authors:Izumi Takahara, Kazunori Nishio, Akira Aiba, Shigeru Kobayashi, Takao Nakajima, Taro Hitosugi, Teruyasu Mizoguchi View a PDF of the paper titled Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents, by Izumi Takahara and 6 other authors View PDF HTML (experimental) Abstract:Self-driving laboratories can explore synthesis conditions autonomously, but their decision-making layer is typically a black-box optimizer, and the output is a set of optimized samples, with the measurements reduced to predefined scalar objectives and the reasons behind success left unarticulated. Here we present SynAgent, a framework in which large language model agents operate an automated experimental system and maintain an explicit, revisable understanding of the synthesis process as the campaign's primary output. Starting with no predefined analysis pipeline, SynAgent adaptively generates analysis skills for newly acquired data and evolves this understanding through multimodal reasoning over experimental data such as X-ray diffraction patterns and electron micrographs. The evolution is guided by a verify-falsify scheme, in which the agent deliberately challenges its own hypotheses by testing conditions predicted to fail as well as those predicted to succeed. In a single campaign of 18 autonomous experiments using LiCoO2 (001) thin-film deposition as a testbed, SynAgent synthesized highly crystalline films and evolved an understanding of how the substrate temperature governs crystallization, discovering an abrupt threshold and a narrow optimal growth window at 650-690 °C. These results extend autonomous experimentation beyond optimized samples to testable, human-readable understanding. Subjects: Materials Science (cond-mat.mtrl-sci); Artificial Intelligence (cs.AI) Cite as: arXiv:2609.18598 [cond-mat.mtrl-sci] (or arXiv:2609.18598v1 [cond-mat.mtrl-sci] for this version) https://doi.org/10.48550/arXiv.2609.18598 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Izumi Takahara [view email] [v1] Wed, 16 Sep 2026 12:52:10 UTC (1,722 KB) Full-text links: Access Paper: View a PDF of the paper titled Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents, by Izumi Takahara and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cond-mat.mtrl-sci new | recent | 2026-09 Change to browse by: cond-mat cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) IArxiv recommender toggle IArxiv Recommender (What is IArxiv?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)