mlsanityData to 14 Oct 2026

Investigating the Potential of Large Language Model-Based Router Multi-Agent Architectures for Foundation Design Automation: A Task Classification and Expert Selection Study

arXiv 2506.13811 ↗First posted 13 Jun 2025cs.MA cs.AI cs.CLcited by 2

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

This study investigates router-based multi-agent systems for automating foundation design calculations through intelligent task classification and expert selection. Three approaches were evaluated: single-agent processing, multi-agent designer-checker architecture, and router-based expert selection. Performance assessment utilized baseline models including DeepSeek R1, ChatGPT 4 Turbo, Grok 3, and Gemini 2.5 Pro across shallow foundation and pile design scenarios. The router-based configuration achieved performance scores of 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 performance respectively. The system outperformed conventional agentic workflows by 10.0 to 43.75 percentage points. Grok 3 demonstrated superior standalone performance without external computational tools, indicating advances in direct LLM mathematical reasoning for engineering applications. The dual-tier classification framework successfully distinguished foundation types, enabling appropriate analytical approaches. Results establish router-based multi-agent systems as optimal for foundation design automation while maintaining professional documentation standards. Given safety-critical requirements in civil engineering, continued human oversight remains essential, positioning these systems as advanced computational assistance tools rather than autonomous design replacements in professional practice.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 3 of its 18 references that are in the map. First posted on arXiv 13 Jun 2025.

Builds on

3 of 18 references.

References · 3

  1. 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planningcited by 207
  2. 2021A Comprehensive Evaluation Framework for Deep Model Robustnesscited by 42
  3. 2023Interactive Design by Integrating a Large Pre-Trained Language Model and Building Information Modelingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Automating Structural Engineering Workflows with Large Language Model Agentscited by 6
  2. 2026What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Taxonomy of Architecture Options for Foundation Model-based Agents: Analysis and Decision Model
  2. 2025Intelligent Design 4.0: Paradigm Evolution Toward the Agentic AI Era
  3. 2026Foundation-Model-Based Agents in Industrial Automation: Purposes, Capabilities, and Open Challenges
  4. 2026Zero-shot adaptable task planning for autonomous construction robots: a comparative study of lightweight single and multi-AI agent systems
  5. 2025DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil Engineering
  6. 2025AgentArcEval: An Architecture Evaluation Method for Foundation Model based Agents
  7. 2026EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible Solutions
  8. 2024Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents