Page 135 - Read Online
P. 135
Li et al. J. Mater. Inf. 2026, 6, 10 Page 27 of 31
39. Robson, M. J.; Xu, S.; Wang, Z.; Chen, Q.; Ciucci, F. Multi-agent-network-based idea generator for zinc-ion battery electrolyte
discovery: a case study on zinc tetrafluoroborate hydrate-based deep eutectic electrolytes. Adv. Mater. 2025, 37, e2502649. DOI PubMed
PMC
40. Ansari, M.; Watchorn, J.; Brown, C. E.; Brown, J. S. dZiner: rational inverse design of materials with AI agents. arXiv 2024,
arXiv:2410.03963. Available online: https://doi.org/10.48550/arXiv.2410.03963 (accessed 22 January 2026).
41. Ghafarollahi, A.; Buehler, M. J. SciAgents: automating scientific discovery through bioinspired multi-agent intelligent graph reasoning.
Adv. Mater. 2025, 37, e2413523. DOI PubMed PMC
42. Baek, J.; Jauhar, S. K.; Cucerzan, S.; Hwang, S. J. ResearchAgent: iterative research idea generation over scientific literature with large
language models. arXiv 2024, arXiv:2404.07738. Available online: https://doi.org/10.48550/arXiv.2404.07738 (accessed 22 January
2026).
43. Ma, Y.; Gou, Z.; Hao, J.; et al. SciAgent: tool-augmented language models for scientific reasoning. arXiv 2024, arXiv:2402.11451.
Available online: https://doi.org/10.48550/arXiv.2402.11451 (accessed 22 January 2026).
44. Yuan, J.; Yan, X.; Feng, S.; et al. Dolphin: moving towards closed-loop auto-research through thinking, practice, and feedback. arXiv
2025, arXiv:2501.03916. Available online: https://doi.org/10.48550/arXiv.2501.03916 (accessed 22 January 2026).
45. Luu, R. K.; Deng, J.; Ibrahim, M. S.; et al. Generative artificial intelligence extracts structure-function relationships from plants for new
materials. arXiv 2025, arXiv:2508.06591. Available online: https://doi.org/10.48550/arXiv.2508.06591 (accessed 22 January 2026).
46. Chen, J.; Saha, S.; Bansal, M. ReConcile: round-table conference improves reasoning via consensus among diverse LLMs. arXiv 2023,
arXiv:2309.13007. Available online: https://doi.org/10.48550/arXiv.2309.13007 (accessed 22 January 2026).
47. Yang, Z.; Liu, W.; Gao, B.; et al. MOOSE-Chem: large language models for rediscovering unseen chemistry scientific hypotheses. arXiv
2024, arXiv:2410.07076. Available online: https://doi.org/10.48550/arXiv.2410.07076 (accessed 22 January 2026).
48. Yang, Z.; Liu, W.; Gao, B.; et al. MOOSE-Chem2: exploring LLM limits in fine-grained scientific hypothesis discovery via hierarchical
search. arXiv 2025, arXiv:2505.19209. Available online: https://doi.org/10.48550/arXiv.2505.19209 (accessed 22 January 2026).
49. Liu, W.; Yang, Z.; Wang, J.; et al. MOOSE-Chem3: toward experiment-guided hypothesis ranking via simulated experimental feedback.
arXiv 2025, arXiv:2505.17873. Available online: https://doi.org/10.48550/arXiv.2505.17873 (accessed 22 January 2026).
50. Schmidgall, S.; Moor, M. AgentRxiv: towards collaborative autonomous research. arXiv 2025, arXiv:2503.18102. Available online: http
s://doi.org/10.48550/arXiv.2503.18102 (accessed 22 January 2026).
51. Pu, Y.; Lin, T.; Chen, H. PiFlow: principle-aware scientific discovery with multi-agent collaboration. arXiv 2025, arXiv:2505.15047.
Available online: https://doi.org/10.48550/arXiv.2505.15047 (accessed 22 January 2026).
52. Lai, Z.; Pu, Y. PriM: principle-inspired material discovery through multi-agent collaboration. arXiv 2025, arXiv:2504.08810. Available
online: https://doi.org/10.48550/arXiv.2504.08810 (accessed 22 January 2026).
53. Madaan, A.; Tandon, N.; Gupta, P.; et al. Self-refine: iterative refinement with self-feedback. In Advances in Neural Information
Processing Systems 36 (NeurIPS 2023), New Orleans, LA, USA, December 10-16, 2023; Oh, A., Naumann, T., Globerson, A., Saenko,
K., Hardt, M., Levine, S., Eds.; Neural Information Processing Systems Foundation, Inc.: Vancouver, Canada; pp 46534-94. Available
online: https://proceedings.neurips.cc/paper_files/paper/2023/hash/91edff07232fb1b55a505a9e9f6c0ff3-Abstract-Conference.html
(accessed 22 January 2026).
54. Su, H.; Chen, R.; Tang, S.; et al. Many heads are better than one: improved scientific idea generation by a LLM-based multi-agent
system. arXiv 2024, arXiv:2410.09403. Available online: https://doi.org/10.48550/arXiv.2410.09403 (accessed 22 January 2026).
55. Ghafarollahi, A.; Buehler, M. J. Sparks: multi-agent artificial intelligence model discovers protein design principles. arXiv 2025,
arXiv:2504.19017. Available online: https://doi.org/10.48550/arXiv.2504.19017 (accessed 22 January 2026).
56. Liu, S.; Lu, Y.; Chen, S.; et al. DrugAgent: automating AI-aided drug discovery programming through LLM multi-agent collaboration.
arXiv 2024, arXiv:2411.15692. Available online: https://doi.org/10.48550/arXiv.2411.15692 (accessed 22 January 2026).
57. Inizan, T. J.; Yang, S.; Kaplan, A.; et al. System of agentic AI for the discovery of metal-organic frameworks. arXiv 2025,
arXiv:2504.14110. Available online: https://doi.org/10.48550/arXiv.2504.14110 (accessed 22 January 2026).
58. Tian, J.; Sobczak, M. T.; Patil, D.; et al. A multi-agent framework integrating large language models and generative AI for accelerated
metamaterial design. arXiv 2025, arXiv:2503.19889. Available online: https://doi.org/10.48550/arXiv.2503.19889 (accessed 22 January
2026).
59. Averly, R.; Baker, F. N.; Watson, I. A.; Ning, X. LIDDIA: language-based intelligent drug discovery agent. arXiv 2025,
arXiv:2502.13959. Available online: https://doi.org/10.48550/arXiv.2502.13959 (accessed 22 January 2026).
60. Bou, A.; Thomas, M.; Dittert, S.; et al. ACEGEN: reinforcement learning of generative chemical agents for drug discovery. J. Chem. Inf.
Model. 2024, 64, 5900-11. DOI PubMed PMC
61. Che, X.; Zhao, Y.; Liu, Q.; Yu, F.; Gao, H.; Zhang, L. CSstep: step-by-step exploration of the chemical space of drug molecules via
multi-agent and multi-stage reinforcement learning. Chem. Eng. Sci. 2025, 317, 122048. DOI
