Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards Responsible Generative AI: A Reference Architecture for Designing Foundation Model based Agents (2311.13148v3)

Published 22 Nov 2023 in cs.AI and cs.SE

Abstract: Foundation models, such as LLMs, have been widely recognised as transformative AI technologies due to their capabilities to understand and generate content, including plans with reasoning capabilities. Foundation model based agents derive their autonomy from the capabilities of foundation models, which enable them to autonomously break down a given goal into a set of manageable tasks and orchestrate task execution to meet the goal. Despite the huge efforts put into building foundation model based agents, the architecture design of the agents has not yet been systematically explored. Also, while there are significant benefits of using agents for planning and execution, there are serious considerations regarding responsible AI related software quality attributes, such as security and accountability. Therefore, this paper presents a pattern-oriented reference architecture that serves as guidance when designing foundation model based agents. We evaluate the completeness and utility of the proposed reference architecture by mapping it to the architecture of two real-world agents.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (69)
  1. OpenAI, “Gpt-4 technical report,” 2023.
  2. 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.
  3. Z. Xi, W. Chen, X. Guo, W. He, Y. Ding, B. Hong, M. Zhang, J. Wang, S. Jin, E. Zhou et al., “The rise and potential of large language model based agents: A survey,” arXiv preprint arXiv:2309.07864, 2023.
  4. L. Wang, C. Ma, X. Feng, Z. Zhang, H. Yang, J. Zhang, Z. Chen, J. Tang, X. Chen, Y. Lin et al., “A survey on large language model based autonomous agents,” arXiv preprint arXiv:2308.11432, 2023.
  5. 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.
  6. ——, “Towards responsible ai in the era of chatgpt: A reference architecture for designing foundation model-based ai systems,” arXiv preprint arXiv:2304.11090, 2023.
  7. S. Hong, X. Zheng, J. Chen, Y. Cheng, C. Zhang, Z. Wang, S. K. S. Yau, Z. Lin, L. Zhou, C. Ran et al., “Metagpt: Meta programming for multi-agent collaborative framework,” arXiv preprint arXiv:2308.00352, 2023.
  8. 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.
  9. 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.
  10. Z. Liu, W. Yao, J. Zhang, L. Xue, S. Heinecke, R. Murthy, Y. Feng, Z. Chen, J. C. Niebles, D. Arpit et al., “Bolaa: Benchmarking and orchestrating llm-augmented autonomous agents,” arXiv preprint arXiv:2308.05960, 2023.
  11. Z. Liu, Y. Zhang, P. Li, Y. Liu, and D. Yang, “Dynamic llm-agent network: An llm-agent collaboration framework with agent team optimization,” arXiv preprint arXiv:2310.02170, 2023.
  12. Z. He, H. Wu, X. Zhang, X. Yao, S. Zheng, H. Zheng, and B. Yu, “Chateda: A large language model powered autonomous agent for eda,” in 2023 ACM/IEEE 5th Workshop on Machine Learning for CAD (MLCAD).   IEEE, 2023, pp. 1–6.
  13. 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.
  14. Y. Liu, S. Chen, H. Chen, M. Yu, X. Ran, A. Mo, Y. Tang, and Y. Huang, “How ai processing delays foster creativity: Exploring research question co-creation with an llm-based agent,” arXiv preprint arXiv:2310.06155, 2023.
  15. S. S. Kannan, V. L. Venkatesh, and B.-C. Min, “Smart-llm: Smart multi-agent robot task planning using large language models,” arXiv preprint arXiv:2309.10062, 2023.
  16. 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.
  17. 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.
  18. C. Zhang, K. Yang, S. Hu, Z. Wang, G. Li, Y. Sun, C. Zhang, Z. Zhang, A. Liu, S.-C. Zhu et al., “Proagent: Building proactive cooperative ai with large language models,” arXiv preprint arXiv:2308.11339, 2023.
  19. Z. Wang, S. Mao, W. Wu, T. Ge, F. Wei, and H. Ji, “Unleashing cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration,” arXiv preprint arXiv:2307.05300, 2023.
  20. G. Li, H. A. A. K. Hammoud, H. Itani, D. Khizbullin, and B. Ghanem, “Camel: Communicative agents for” mind” exploration of large scale language model society,” arXiv preprint arXiv:2303.17760, 2023.
  21. A. Zhao, D. Huang, Q. Xu, M. Lin, Y.-J. Liu, and G. Huang, “Expel: Llm agents are experiential learners,” arXiv preprint arXiv:2308.10144, 2023.
  22. R. Schumann, W. Zhu, W. Feng, T.-J. Fu, S. Riezler, and W. Y. Wang, “Velma: Verbalization embodiment of llm agents for vision and language navigation in street view,” arXiv preprint arXiv:2307.06082, 2023.
  23. C. Packer, V. Fang, S. G. Patil, K. Lin, S. Wooders, and J. E. Gonzalez, “Memgpt: Towards llms as operating systems,” arXiv preprint arXiv:2310.08560, 2023.
  24. Y. Jin, X. Shen, H. Peng, X. Liu, J. Qin, J. Li, J. Xie, P. Gao, G. Zhou, and J. Gong, “Surrealdriver: Designing generative driver agent simulation framework in urban contexts based on large language model,” arXiv preprint arXiv:2309.13193, 2023.
  25. H. Zhang, W. Du, J. Shan, Q. Zhou, Y. Du, J. B. Tenenbaum, T. Shu, and C. Gan, “Building cooperative embodied agents modularly with large language models,” arXiv preprint arXiv:2307.02485, 2023.
  26. Y. Ye, X. Cong, S. Tian, J. Cao, H. Wang, Y. Qin, Y. Lu, H. Yu, H. Wang, Y. Lin et al., “Proagent: From robotic process automation to agentic process automation,” arXiv preprint arXiv:2311.10751, 2023.
  27. J. Wei, X. Wang, D. Schuurmans, M. Bosma, F. Xia, E. Chi, Q. V. Le, D. Zhou et al., “Chain-of-thought prompting elicits reasoning in large language models,” Advances in Neural Information Processing Systems, vol. 35, pp. 24 824–24 837, 2022.
  28. Z. Wang, Z. Liu, Y. Zhang, A. Zhong, L. Fan, L. Wu, and Q. Wen, “Rcagent: Cloud root cause analysis by autonomous agents with tool-augmented large language models,” arXiv preprint arXiv:2310.16340, 2023.
  29. X. Wang, J. Wei, D. Schuurmans, Q. Le, E. Chi, S. Narang, A. Chowdhery, and D. Zhou, “Self-consistency improves chain of thought reasoning in language models,” arXiv preprint arXiv:2203.11171, 2022.
  30. S. Yao, D. Yu, J. Zhao, I. Shafran, T. L. Griffiths, Y. Cao, and K. Narasimhan, “Tree of thoughts: Deliberate problem solving with large language models,” arXiv preprint arXiv:2305.10601, 2023.
  31. J. S. Park, J. O’Brien, C. J. Cai, M. R. Morris, P. Liang, and M. S. Bernstein, “Generative agents: Interactive simulacra of human behavior,” in Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, 2023, pp. 1–22.
  32. S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K. Narasimhan, and Y. Cao, “React: Synergizing reasoning and acting in language models,” arXiv preprint arXiv:2210.03629, 2022.
  33. A. Madaan, N. Tandon, P. Gupta, S. Hallinan, L. Gao, S. Wiegreffe, U. Alon, N. Dziri, S. Prabhumoye, Y. Yang et al., “Self-refine: Iterative refinement with self-feedback,” arXiv preprint arXiv:2303.17651, 2023.
  34. T. Sumers, S. Yao, K. Narasimhan, and T. L. Griffiths, “Cognitive architectures for language agents,” arXiv preprint arXiv:2309.02427, 2023.
  35. N. Shinn, B. Labash, and A. Gopinath, “Reflexion: an autonomous agent with dynamic memory and self-reflection,” arXiv preprint arXiv:2303.11366, 2023.
  36. P.-L. Chen and C.-S. Chang, “Interact: Exploring the potentials of chatgpt as a cooperative agent,” arXiv preprint arXiv:2308.01552, 2023.
  37. Y. Talebirad and A. Nadiri, “Multi-agent collaboration: Harnessing the power of intelligent llm agents,” arXiv preprint arXiv:2306.03314, 2023.
  38. W. Huang, F. Xia, T. Xiao, H. Chan, J. Liang, P. Florence, A. Zeng, J. Tompson, I. Mordatch, Y. Chebotar et al., “Inner monologue: Embodied reasoning through planning with language models,” arXiv preprint arXiv:2207.05608, 2022.
  39. G. Sarch, Y. Wu, M. J. Tarr, and K. Fragkiadaki, “Open-ended instructable embodied agents with memory-augmented large language models,” arXiv preprint arXiv:2310.15127, 2023.
  40. G. Chen, S. Dong, Y. Shu, G. Zhang, J. Sesay, B. F. Karlsson, J. Fu, and Y. Shi, “Autoagents: A framework for automatic agent generation,” arXiv preprint arXiv:2309.17288, 2023.
  41. N. Nascimento, P. Alencar, and D. Cowan, “Self-adaptive large language model (llm)-based multiagent systems,” arXiv preprint arXiv:2307.06187, 2023.
  42. 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.
  43. Y. Kong, J. Ruan, Y. Chen, B. Zhang, T. Bao, S. Shi, G. Du, X. Hu, H. Mao, Z. Li et al., “Tptu-v2: Boosting task planning and tool usage of large language model-based agents in real-world systems,” arXiv preprint arXiv:2311.11315, 2023.
  44. T. Xie, F. Zhou, Z. Cheng, P. Shi, L. Weng, Y. Liu, T. J. Hua, J. Zhao, Q. Liu, C. Liu et al., “Openagents: An open platform for language agents in the wild,” arXiv preprint arXiv:2310.10634, 2023.
  45. G. Wang, Y. Xie, Y. Jiang, A. Mandlekar, C. Xiao, Y. Zhu, L. Fan, and A. Anandkumar, “Voyager: An open-ended embodied agent with large language models,” arXiv preprint arXiv:2305.16291, 2023.
  46. C. Qian, C. Han, Y. R. Fung, Y. Qin, Z. Liu, and H. Ji, “Creator: Disentangling abstract and concrete reasonings of large language models through tool creation,” arXiv preprint arXiv:2305.14318, 2023.
  47. M. Chen, J. Tworek, H. Jun, Q. Yuan, H. P. d. O. Pinto, J. Kaplan, H. Edwards, Y. Burda, N. Joseph, G. Brockman et al., “Evaluating large language models trained on code,” arXiv preprint arXiv:2107.03374, 2021.
  48. S. Hamilton, “Blind judgement: Agent-based supreme court modelling with gpt,” arXiv preprint arXiv:2301.05327, 2023.
  49. C. Qian, X. Cong, C. Yang, W. Chen, Y. Su, J. Xu, Z. Liu, and M. Sun, “Communicative agents for software development,” arXiv preprint arXiv:2307.07924, 2023.
  50. Y. Li, Y. Zhang, and L. Sun, “Metaagents: Simulating interactions of human behaviors for llm-based task-oriented coordination via collaborative generative agents,” arXiv preprint arXiv:2310.06500, 2023.
  51. J. Chen, S. Yuan, R. Ye, B. P. Majumder, and K. Richardson, “Put your money where your mouth is: Evaluating strategic planning and execution of llm agents in an auction arena,” arXiv preprint arXiv:2310.05746, 2023.
  52. Q. Zhao, J. Wang, Y. Zhang, Y. Jin, K. Zhu, H. Chen, and X. Xie, “Competeai: Understanding the competition behaviors in large language model-based agents,” arXiv preprint arXiv:2310.17512, 2023.
  53. Y. Du, S. Li, A. Torralba, J. B. Tenenbaum, and I. Mordatch, “Improving factuality and reasoning in language models through multiagent debate,” arXiv preprint arXiv:2305.14325, 2023.
  54. T. Liang, Z. He, W. Jiao, X. Wang, Y. Wang, R. Wang, Y. Yang, Z. Tu, and S. Shi, “Encouraging divergent thinking in large language models through multi-agent debate,” arXiv preprint arXiv:2305.19118, 2023.
  55. H. Chen, W. Ji, L. Xu, and S. Zhao, “Multi-agent consensus seeking via large language models,” arXiv preprint arXiv:2310.20151, 2023.
  56. X. Tang, A. Zou, Z. Zhang, Y. Zhao, X. Zhang, A. Cohan, and M. Gerstein, “Medagents: Large language models as collaborators for zero-shot medical reasoning,” arXiv preprint arXiv:2311.10537, 2023.
  57. 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.
  58. 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.
  59. B. Xia, Q. Lu, L. Zhu, S. U. Lee, Y. Liu, and Z. Xing, “From principles to practice: An accountability metrics catalogue for managing ai risks,” arXiv preprint arXiv:2311.13158, 2023.
  60. Z. Yang, S. S. Raman, A. Shah, and S. Tellex, “Plug in the safety chip: Enforcing constraints for llm-driven robot agents,” arXiv preprint arXiv:2309.09919, 2023.
  61. M. Abbasian, I. Azimi, A. M. Rahmani, and R. Jain, “Conversational health agents: A personalized llm-powered agent framework,” arXiv preprint arXiv:2310.02374, 2023.
  62. Z. Wang, S. Cai, A. Liu, X. Ma, and Y. Liang, “Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents,” arXiv preprint arXiv:2302.01560, 2023.
  63. S. Schwartz, A. Yaeli, and S. Shlomov, “Enhancing trust in llm-based ai automation agents: New considerations and future challenges,” arXiv preprint arXiv:2308.05391, 2023.
  64. B. Xia, D. Zhang, Y. Liu, Q. Lu, Z. Xing, and L. Zhu, “Trust in software supply chains: Blockchain-enabled sbom and the aibom future,” arXiv preprint arXiv:2307.02088, 2023.
  65. B. Xia, T. Bi, Z. Xing, Q. Lu, and L. Zhu, “An empirical study on software bill of materials: Where we stand and the road ahead,” arXiv preprint arXiv:2301.05362, 2023.
  66. B. Y. Lin, Y. Fu, K. Yang, P. Ammanabrolu, F. Brahman, S. Huang, C. Bhagavatula, Y. Choi, and X. Ren, “Swiftsage: A generative agent with fast and slow thinking for complex interactive tasks,” arXiv preprint arXiv:2305.17390, 2023.
  67. M. Nafreen, S. Bhattacharya, and L. Fiondella, “Architecture-based software reliability incorporating fault tolerant machine learning,” in 2020 Annual Reliability and Maintainability Symposium (RAMS).   IEEE, 2020, pp. 1–6.
  68. Y. Cheng, J. Chen, Q. Huang, Z. Xing, X. Xu, and Q. Lu, “Prompt sapper: A llm-empowered production tool for building ai chains,” arXiv preprint arXiv:2306.12028, 2023.
  69. F. Costantino, S. Colabianchi, and A. Tedeschi, “Human-technology integration with industrial conversational agents: A conceptual architecture and a taxonomy for manufacturing,” Available at SSRN 4285483.
Citations (7)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Youtube Logo Streamline Icon: https://streamlinehq.com

YouTube