A Reference Architecture for Designing Foundation Model based Systems (2304.11090v5)
Abstract: The release of ChatGPT, Gemini, and other LLM has drawn huge interests on foundations models. There is a broad consensus that foundations models will be the fundamental building blocks for future AI systems. However, there is a lack of systematic guidance on the architecture design. Particularly, the the rapidly growing capabilities of foundations models can eventually absorb other components of AI systems, posing challenges of moving boundary and interface evolution in architecture design. Furthermore, incorporating foundations models into AI systems raises significant concerns about responsible and safe AI due to their opaque nature and rapidly advancing intelligence. To address these challenges, the paper first presents an architecture evolution of AI systems in the era of foundation models, transitioning from "foundation-model-as-a-connector" to "foundation-model-as-a-monolithic architecture". The paper then identifies key design decisions and proposes a pattern-oriented reference architecture for designing responsible foundation-model-based systems. The patterns can enable the potential of foundation models while ensuring associated risks.
- R. Bommasani, D. A. Hudson, E. Adeli, R. Altman, S. Arora, S. von Arx, M. S. Bernstein, J. Bohg, A. Bosselut, E. Brunskill et al., “On the opportunities and risks of foundation models,” arXiv preprint arXiv:2108.07258, 2021.
- Q. Lu, L. Zhu, X. Xu, Z. Xing, and J. Whittle, “A framework for designing foundation model based systems,” arXiv preprint arXiv:2305.05352, 2023.
- Y. Shen, K. Song, X. Tan, D. Li, W. Lu, and Y. Zhuang, “Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface,” arXiv preprint arXiv:2303.17580, 2023.
- A. Zeng, A. Wong, S. Welker, K. Choromanski, F. Tombari, A. Purohit, M. Ryoo, V. Sindhwani, J. Lee, V. Vanhoucke et al., “Socratic models: Composing zero-shot multimodal reasoning with language,” arXiv preprint arXiv:2204.00598, 2022.
- D. Driess, F. Xia, M. S. Sajjadi, C. Lynch, A. Chowdhery, B. Ichter, A. Wahid, J. Tompson, Q. Vuong, T. Yu et al., “Palm-e: An embodied multimodal language model,” arXiv preprint arXiv:2303.03378, 2023.
- ISO/IEC, “Iso/iec 25010:2011 - systems and software engineering. systems and software quality requirements and evaluation (square). system and software quality models,” 2011.
- J. Ruan, Y. Chen, B. Zhang, Z. Xu, T. Bao, G. Du, S. Shi, H. Mao, X. Zeng, and R. Zhao, “Tptu: Task planning and tool usage of large language model-based ai agents,” arXiv preprint arXiv:2308.03427, 2023.
- Y. Xia, M. Shenoy, N. Jazdi, and M. Weyrich, “Towards autonomous system: flexible modular production system enhanced with large language model agents,” arXiv preprint arXiv:2304.14721, 2023.
- D. Zhao, Z. Xing, X. Xia, D. Ye, X. Xu, and L. Zhu, “Seehow: Workflow extraction from programming screencasts through action-aware video analytics,” arXiv preprint arXiv:2304.14042, 2023.
- X. Zeng, X. Wang, T. Zhang, C. Yu, S. Zhao, and Y. Chen, “Gesturegpt: Zero-shot interactive gesture understanding and grounding with large language model agents,” arXiv preprint arXiv:2310.12821, 2023.
- M. Galster and P. Avgeriou, “Empirically-grounded reference architectures: a proposal,” in Proceedings of the joint ACM SIGSOFT conference–QoSA and ACM SIGSOFT symposium–ISARCS on Quality of software architectures–QoSA and architecting critical systems–ISARCS, 2011, pp. 153–158.
- Q. Lu, L. Zhu, X. Xu, J. Whittle, D. Zowghi, and A. Jacquet, “Responsible ai pattern catalogue: A collection of best practices for ai governance and engineering,” ACM Computing Surveys, 2022.
- F. Bachmann, L. Bass, and R. Nord, “Modifiability tactics,” CARNEGIE-MELLON UNIV PITTSBURGH PA SOFTWARE ENGINEERING INST, Tech. Rep., 2007.
- G. Falco and J. E. Siegel, “A distributedblack box’audit trail design specification for connected and automated vehicle data and software assurance,” arXiv preprint arXiv:2002.02780, 2020.
- S. U. Lee, H. Perera, B. Xia, Y. Liu, Q. Lu, L. Zhu, O. Salvado, and J. Whittle, “Qb4aira: A question bank for ai risk assessment,” arXiv preprint arXiv:2305.09300, 2023.