用Gemini打造科研伙伴，实现从假说到实验的全流程自动化。
Accelerating Scientific Research with Gemini in the Real-World
- 构建基于Gemini的多智能体系统，实现科学假说生成、实验执行与论文撰写闭环。
- 在材料、生物、计算机三领域完成真实实验，成功制备二维半导体并预测细菌行为。
- 通过双盲测试验证其可靠性，显著降低幻觉和抄袭，适合需要加速研究的团队。
我们拓展并全面验证了Co-Scientist——一个基于Gemini的多智能体系统，旨在加速跨领域的端到端科学研究，涵盖假说生成、实验执行和论文撰写。该系统突破纯模拟假说生成，转向以实验为驱动的研究模式，在材料科学中对接半自动化学气相沉积反应器，设计出一种安全前驱体路径，成功制备出与Ti3C2Tx MXene结构相似的层状二维材料，但原子结构仍需进一步验证。利用Gemini 3 Deep Think实现实验室内快速闭环执行，仅数分钟即定制出符合实验条件的生长配方，一次性获得单层MoS2、MoSe2和WS2半导体。在生物学中，基于稀疏成像数据预测工程化大肠杆菌在IPTG梯度下的群体行为，定量匹配未发表的湿实验形态测量结果。在计算机科学中，自主发现一种推理时缩放架构，在HealthBench（Hard与Professional）上优于六个前沿模型，且在盲评医生评估中降低潜在临床危害。最后，对30名领域专家进行双盲评审，共450份评价显示，其可靠性模块有效减少幻觉与剽窃，提升研究安全性。这些结果表明，闭环多智能体科学人工智能系统正迈向真实世界科研加速。
原文摘要 · Abstract (English)
We present an extension and comprehensive real-world validation of Co-Scientist, a Gemini-based multi-agent system designed to accelerate end-to-end scientific research across hypothesis generation, experimentation, and manuscript generation. Moving beyond in silico hypothesis generation, this specialized configuration transitions Co-Scientist into an execution-grounded research partner advancing closed-loop scientific workflows across materials science, biology, and computer science. In materials science, Co-Scientist interfaced with a semi-automated chemical vapor deposition reactor to design a safe precursor route for MXenes; experimental execution produced a lamellar 2D material sharing key structural similarities with the Ti3C2Tx MXene lattice, although further experiments are needed to confirm the atomic structure. Leveraging Gemini 3 Deep Think for rapid, lab-in-the-loop execution, it also tailored growth recipes to laboratory constraints in minutes, enabling single-attempt growth of monolayer MoS2, MoSe2, and WS2 semiconductors. In biology, Co-Scientist predicted emergent swarming phenotypes of engineered E. coli across inducer (IPTG) gradients from sparse imaging data, quantitatively matching unpublished wet-lab morphological measurements. In computer science, Co-Scientist autonomously discovered an inference-time scaling architecture that outperformed six frontier models on HealthBench (Hard and Professional) while reducing potential clinical harm under blinded physician evaluation. Finally, a double-blind study of end-to-end generated papers with 30 domain experts across 450 reviews demonstrates that Co-Scientist's reliability modules reduce hallucination and plagiarism while improving research safety. Together, these results demonstrate progress toward closed-loop multi-agent scientific AI systems capable of accelerating real-world scientific discovery.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。