# Agentic Large Language Models for Conceptual Systems Engineering and Design

arXiv: https://arxiv.org/abs/2507.08619 · HTML: https://mlsanity.com/paper/2507.08619/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 27 of its 70 references that are in the map.
- First posted on arXiv 11 Jul 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 27 of 27)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [Effective Long-Context Scaling of Foundation Models](https://mlsanity.com/paper/2309.16039/) (2023)
- [Empowering Biomedical Discovery with AI Agents](https://mlsanity.com/paper/2404.02831/) (2024)
- [Deep Generative Models in Engineering Design: A Review](https://mlsanity.com/paper/2110.10863/) (2021)
- [Diffusion Models Beat GANs on Topology Optimization](https://mlsanity.com/paper/2208.09591/) (2022)
- [Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation](https://mlsanity.com/paper/2305.18470/) (2023)
- [From Concept to Manufacturing: Evaluating Vision-Language Models for Engineering Design](https://mlsanity.com/paper/2311.12668/) (2023)
- [DesignQA: A Multimodal Benchmark for Evaluating Large Language Models' Understanding of Engineering Documentation](https://mlsanity.com/paper/2404.07917/) (2024)
- [AI Agents in Engineering Design: A Multi-Agent Framework for Aesthetic and Aerodynamic Car Design](https://mlsanity.com/paper/2503.23315/) (2025)
- [A Human-Like Reasoning Framework for Multi-Phases Planning Task with Large Language Models](https://mlsanity.com/paper/2405.18208/) (2024)
- [B'ezierGAN: Automatic Generation of Smooth Curves from Interpretable Low-Dimensional Parameters](https://mlsanity.com/paper/1808.08871/) (2018)
- [Trust at Your Own Peril: A Mixed Methods Exploration of the Ability of Large Language Models to Generate Expert-Like Systems Engineering Artifacts and a Characterization of Failure Modes](https://mlsanity.com/paper/2502.09690/) (2025)
- [A hybrid numerical methodology coupling Reduced Order Modeling and Graph Neural Networks for non-parametric geometries: applications to structural dynamics problems](https://mlsanity.com/paper/2406.02615/) (2024)
- [Inverse design with conditional cascaded diffusion models](https://mlsanity.com/paper/2408.08526/) (2024)
- [Complex System Design with Design Languages: Method, Applications and Design Principles](https://mlsanity.com/paper/1805.09111/) (2018)

## Built on by (most cited first, 7 of 7)

- [Toward Autonomous Engineering Design: A Knowledge-Guided Multi-Agent Framework](https://mlsanity.com/paper/2511.03179/) (2025)
- [Supervising Ralph Wiggum: Exploring a Metacognitive Co-Regulation Agentic AI Loop for Engineering Design](https://mlsanity.com/paper/2603.24768/) (2026)
- [EngiAI: Capability-Based Evaluation of Tool-Connected LLM Agents for Engineering Design](https://mlsanity.com/paper/2605.19743/) (2026)
- [TurboAgent: An LLM-Driven Autonomous Multi-Agent Framework for Turbomachinery Aerodynamic Design](https://mlsanity.com/paper/2604.06747/) (2026)
- [Design-OS: A Specification-Driven Framework for Engineering System Design with a Control-Systems Design Case](https://mlsanity.com/paper/2603.20151/) (2026)
- [Agentic Risk-Aware Set-Based Engineering Design](https://mlsanity.com/paper/2604.16687/) (2026)
- [TO-Agents: A Multi-Agent AI Framework for Subjective Preference-Guided Topology Optimization](https://mlsanity.com/paper/2605.21622/) (2026)

## Abstract (arXiv)

Early-stage engineering design involves complex, iterative reasoning, yet existing large language model (LLM) workflows struggle to maintain task continuity and generate executable models. We evaluate whether a structured multi-agent system (MAS) can more effectively manage requirements extraction, functional decomposition, and simulator code generation than a simpler two-agent system (2AS). The target application is a solar-powered water filtration system as described in a cahier des charges. We introduce the Design-State Graph (DSG), a JSON-serializable representation that bundles requirements, physical embodiments, and Python-based physics models into graph nodes. A nine-role MAS iteratively builds and refines the DSG, while the 2AS collapses the process to a Generator-Reflector loop. Both systems run a total of 60 experiments (2 LLMs - Llama 3.3 70B vs reasoning-distilled DeepSeek R1 70B x 2 agent configurations x 3 temperatures x 5 seeds). We report a JSON validity, requirement coverage, embodiment presence, code compatibility, workflow completion, runtime, and graph size. Across all runs, both MAS and 2AS maintained perfect JSON integrity and embodiment tagging. Requirement coverage remained minimal (less than 20%). Code compatibility peaked at 100% under specific 2AS settings but averaged below 50% for MAS. Only the reasoning-distilled model reliably flagged workflow completion. Powered by DeepSeek R1 70B, the MAS generated more granular DSGs (average 5-6 nodes) whereas 2AS mode-collapsed. Structured multi-agent orchestration enhanced design detail. Reasoning-distilled LLM improved completion rates, yet low requirements and fidelity gaps in coding persisted.