The Copilot for Real-world Experimental Scientist (CRESt) system empowers researchers to control autonomous laboratories through conversational AI, providing a seamless interface for managing complex experimental workflows. We have enhanced CRESt by integrating a multi-agent collaboration mechanism that utilizes the complementary strengths of the ChatGPT and Gemini models for precise image analysis in materials science. This innovative approach significantly improves the accuracy of experimental outcomes by fostering structured debates between the AI models, which enhances decision-making processes in materials phase analysis. Additionally, to evaluate the generalizability of this approach, we tested it on a quantitative task of counting particles. Here, the collaboration between the AI models also led to improved results, demonstrating the versatility and robustness of this method. By harnessing this dual-AI framework, this approach stands as a pioneering method for enhancing experimental accuracy and efficiency in materials research, with applications extending beyond CRESt to broader scientific experimentation and analysis.
- Open Access
- Article
Collaborative AI Enhances Image Understanding in Materials Science
- Ruoyan Avery Yin 1,
- Zhichu Ren 2,*,
- Zongyou Yin 3,
- Zhen Zhang 2,
- So Yeon Kim 2,
- Chia-Wei Hsu 2,
- Ju Li 2,*
Author Information
Received: 30 Nov 2025 | Revised: 17 Dec 2025 | Accepted: 23 Dec 2025 | Published: 22 Jan 2026
Abstract
Keywords
computing methodologies | collaborative AI | image analysis | prompt engineering | ChatGPT | Gemini
References
- 1.
Bi, W.L.; Hosny, A.; Schabath, M.B.; et al. Artificial intelligence in cancer imaging: Clinical challenges and applications. CA Cancer J. Clin. 2019, 69, 127–157.
- 2.
Hosny, A.; Parmar, C.; Quackenbush, J.; et al. Artificial intelligence in radiology. Nat. Rev. Cancer 2018, 18, 500–510.
- 3.
Ibrahim, M.R.; Haworth, J.; Cheng, T. Understanding cities with machine eyes: A review of deep computer vision in urban analytics. Cities 2020, 96, 102481.
- 4.
Hennessey, E.; DiFazio, M.; Hennessey, R.; et al. Artificial intelligence in veterinary diagnostic imaging: A literature review. Vet. Radiol. Ultrasound 2022, 63, 851–870.
- 5.
Du, Y.; Li, S.; Torralba, A.; et al. Improving factuality and reasoning in language models through multiagent debate. arXiv 2023, arXiv: 2305.14325.
- 6.
Wang, J.; Liu, Z.; Zhao, L.; et al. Review of large vision models and visual prompt engineering. Meta-Radiol. 2023, 1, 100047.
- 7.
Garikipati, A.; Maharjan, J.; Singh, N.P.; et al. OpenMedLM: Prompt engineering can out-perform fine-tuning in medical question-answering with open-source large language models. In Proceedings of the AAAI 2024 Spring Symposium on Clinical Foundation Models, Stanford, CA, USA, 25–27 March 2024.
- 8.
Ren, Z.; Zhang, Z.; Tian, Y.; et al. Crest–copilot for real-world experimental scientist. ChemRxiv 2023. https://doi.org/10.26434/chemrxiv-2023-tnz1x.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com