Large language model-based multi-agent systems for automated foundation design: router-driven task classification and expert selection framework

Abstract

This preliminary study introduces and evaluates a router-based multi-agent framework for automated foundation design calculations through intelligent task classification and expert selection. Three configurations were assessed: single-agent processing, multi-agent designer-checker architecture, and router-based expert selection, using baseline models including DeepSeek R1, ChatGPT 4 Turbo, Grok 3, and Gemini 2.5 Pro. Initial evaluation on 27 test cases with triple-trial execution shows promising performance: the router-based system achieved 95.00% for shallow foundations and 90.63% for pile design, representing improvements of 8.75 and 3.13 percentage points over standalone Grok 3, respectively, and outperforming conventional workflows by 10.0–43.75 percentage points. Grok 3 demonstrated superior standalone performance, indicating enhanced large language model (LLM) mathematical reasoning capabilities. The dual-tier classification framework successfully distinguished foundation types, enabling appropriate analytical approaches. While these preliminary results suggest router-based multi-agent systems as a promising approach for foundation design automation, the limited sample size necessitates comprehensive validation on larger, more diverse datasets before deployment recommendations. Safety–critical requirements necessitate continued human oversight in professional applications. This work provides a methodological foundation for future research in AI-assisted geotechnical engineering.

Keywords

Router / Based multi / Agent systems / Large language models / Foundation design / Geotechnical engineering / Task classification / Expert selection / AI / Assisted engineering

References

[1] Baghbani A, Choudhury T, Costa S, Reiner J. Application of artificial intelligence in geotechnical engineering: A state-of-the-art review. Earth-Science Reviews. 2022, 228. 103991

[2] Chen L, Tophel A, Hettiyadura U, Kodikara J. An investigation into the utility of large language models in geotechnical education and problem solving. Geotechnics. 2024, 4(2): 470-498.

[3] DeepSeek-AI. (2025). DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning (No. arXiv:2501.12948). arXiv. https://doi.org/10.48550/arXiv.2501.12948

[4] Google DeepMind. (2025). Gemini 2.5: Our newest Gemini model with thinking. https://blog.google/technology/google-deepmind/gemini-model-thinking-updates-march-2025/

[5] Guan, L., Valmeekam, K., Sreedharan, S., & Kambhampati, S. (2023). Leveraging pre-trained large language models to construct and utilize world models for model-based task planning (Version 2). arXiv. https://doi.org/10.48550/ARXIV.2305.14909

[6] Guo J, Bao W, Wang J, Ma Y, Gao X, Xiao G, Liu A, Dong J, Liu X, Wu W. A comprehensive evaluation framework for deep model robustness. Pattern Recognition. 2023, 137. 109308

[7] Han D, Zhao W, Yin H, Qu M, Zhu J, Ma F, Ying Y, Pan A. Large language models driven BIM-based DfMA method for free-form prefabricated buildings: Framework and a usefulness case study. Journal of Asian Architecture and Building Engineering. 2025, 24(3): 1500-1517.

[8] Herrera M, Pérez-Hernández M, Kumar A, Tchernykh A. Multi-agent systems and complex networks: Review and applications in systems engineering. Processes. 2020, 8(3): 312.

[9] IEEE. (2024). IEEE standard for robustness evaluation test methods for a natural language processing service that uses machine learning (No. IEEE Std 3168–2024). IEEE. https://doi.org/10.1109/IEEESTD.2024.10636902

[10] Jang S, Lee G. Interactive design by integrating a large pre-trained language model and building information modeling. Computing in Civil Engineering. 2024, 2023: 291-299.

[11] Joffe I, Felobes G, Elgouhari Y, Talebi Kalaleh M, Mei Q, Chui YH. The framework and implementation of using large language models to answer questions about building codes and standards. Journal of Computing in Civil Engineering. 2025, 394. 05025004

[12] Kampelopoulos D, Tsanousa A, Vrochidis S, Kompatsiaris I. A review of LLMs and their applications in the architecture, engineering and construction industry. Artificial Intelligence Review. 2025, 588. 250

[13] Khedher MI, Jmila H, El Yacoubi M. On the formal evaluation of the robustness of neural networks and its pivotal relevance for ai-based safety-critical domains. International Journal of Network Dynamics and Intelligence. 2023.

[14] Liang, H., Kalaleh, M. T., & Mei, Q. (2025). Integrating large language models for automated structural analysis (No. arXiv:2504.09754). arXiv. https://doi.org/10.48550/arXiv.2504.09754

[15] n8n GmbH. (2025). n8n: Workflow automation platform. https://n8n.io/

[16] OpenAI. (2023). GPT-4 Technical Report. https://doi.org/10.48550/ARXIV.2303.08774

[17] OpenRouter. (2024). OpenRouter: Find the best LLM for your use case. https://openrouter.ai

[18] Pu H, Yang X, Li J, Guo R. AutoRepo: A general framework for multimodal LLM-based automated construction reporting. Expert Systems with Applications. 2024, 255. 124601

[19] Salvador Palau A, Dhada MH, Parlikad AK. Multi-agent system architectures for collaborative prognostics. Journal of Intelligent Manufacturing. 2019, 3082999-3013.

[20] SerpApi. (2024). SerpApi: Google Search API. https://serpapi.com/

[21] Shakshuki E, Reid M. Intelligent multi-agent systems for advanced geotechnical monitoring. In advanced geotechnical engineering. 2023, London, IntechOpen.

[22] Smetana M, Salles De Salles L, Sukharev I, Khazanovich L. Highway construction safety analysis using large language models. Applied Sciences. 2024, 14(4. 1352

[23] Uddin SMJ, Albert A, Ovid A, Alsharef A. Leveraging ChatGPT to aid construction hazard recognition and support safety education and training. Sustainability. 2023, 159. 7121

[24] Vesic, A. S. (1977). Design of pile foundations (No. NCHRP Synthesis 42; p. 68). National Cooperative Highway Research Program. https://onlinepubs.trb.org/Onlinepubs/nchrp/nchrp_syn_42.pdf

[25] Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models (Version 6). arXiv. https://doi.org/10.48550/ARXIV.2201.11903

[26] xAI. (2025). Grok 3 Beta—The Age of Reasoning Agents. https://x.ai/news/grok-3

[27] Xu H-R, Zhang N, Yin Z-Y, Njock PGA. Multimodal framework integrating multiple large language model agents for intelligent geotechnical design. Automation in Construction. 2025, 176. 106257

[28] Yang, H., Siew, M., & Joe-Wong, C. (2024). An LLM-Based Digital Twin for Optimizing Human-in-the Loop Systems (Version 1). arXiv. https://doi.org/10.48550/ARXIV.2403.16809

[29] Yousefpour N, Liu Z, Zhao C. Machine learning methods for geotechnical site characterization and scour assessment. Transportation Research Record: Journal of the Transportation Research Board. 2025, 26791): 632-655.

[30] Zhang H-J, Chen C-C, Ran P, Yang K, Liu Q-C, Sun Z-Y, Chen J, Chen J-K. A multi-dimensional hierarchical evaluation system for data quality in trustworthy AI. Journal of Big Data. 2024, 111. 136

RIGHTS & PERMISSIONS

The Author(s)