TurboAgent: An LLM-Driven Autonomous Multi-Agent Framework for Turbomachinery Aerodynamic Design

• URL: http://arxiv.org/abs/2604.06747v2
• Date: Thu, 09 Apr 2026 03:04:35 GMT
• Title: TurboAgent: An LLM-Driven Autonomous Multi-Agent Framework for Turbomachinery Aerodynamic Design
• Abstract summary: TurboAgent is a large language model (LLM)-driven autonomous multi-agent framework for turbomachinery aerodynamic design and optimization.<n>The framework transforms traditional trial-and-error design into a data-driven collaborative workflow, with high-fidelity simulations retained for final verification.
• Score: 13.755754877323348
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The aerodynamic design of turbomachinery is a complex and tightly coupled multi-stage process involving geometry generation, performance prediction, optimization, and high-fidelity physical validation. Existing intelligent design approaches typically focus on individual stages or rely on loosely coupled pipelines, making fully autonomous end-to-end design challenging. To address this issue, this study proposes TurboAgent, a large language model (LLM)-driven autonomous multi-agent framework for turbomachinery aerodynamic design and optimization. The LLM serves as the core for task planning and coordination, while specialized agents handle generative design, rapid performance prediction, multi-objective optimization, and physics-based validation. The framework transforms traditional trial-and-error design into a data-driven collaborative workflow, with high-fidelity simulations retained for final verification. A transonic single-rotor compressor is used for validation. The results show strong agreement between target performance, generated designs, and CFD simulations. The coefficients of determination for mass flow rate, total pressure ratio, and isentropic efficiency all exceed 0.91, with normalized RMSE values below 8%. The optimization agent further improves isentropic efficiency by 1.61% and total pressure ratio by 3.02%. The complete workflow can be executed within approximately 30 minutes under parallel computing. These results demonstrate that TurboAgent enables an autonomous closed-loop design process from natural language requirements to final design generation, providing an efficient and scalable paradigm for turbomachinery aerodynamic design.

Related papers

• AI-Driven Performance-to-Design Generation and Optimization of Marine Propellers [0.3868072865207522]
  Application to marine propeller design remains challenging due to scarce training data and the lack of widely available pretrained models.<n>We build a database of over 20,000 four- and five-bladed propeller geometries, each accompanied by simulated open-water performance curves.<n>We develop a generative-AI framework for direct performance-to-design generation tailored to marine propellers.
  arXiv  Detail & Related papers  (2026-04-24T05:01:21Z)
• Generalized Task-Driven Design of Soft Robots via Reduced-Order FEM-based Surrogate Modeling [8.36237361666539]
  This paper presents a unified reduced-order finite element method (FEM)-based surrogate modeling pipeline for task-driven soft robot design.<n>High-fidelity FEM simulations characterize actuator behavior at the modular level, from which compact surrogate joint models are constructed.<n>A meta-model maps actuator design parameters to surrogate representations, enabling rapid instantiation across a parameterized actuator family.
  arXiv  Detail & Related papers  (2026-03-20T09:33:09Z)
• EmboCoach-Bench: Benchmarking AI Agents on Developing Embodied Robots [68.29056647487519]
  Embodied AI is fueled by high-fidelity simulation and large-scale data collection.<n>However, this scaling capability remains bottlenecked by a reliance on labor-intensive manual oversight.<n>We introduce textscEmboCoach-Bench, a benchmark evaluating the capacity of LLM agents to autonomously engineer embodied policies.
  arXiv  Detail & Related papers  (2026-01-29T11:33:49Z)
• AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent [80.83250816918861]
  Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in natural language reasoning with long chain-of-thought.<n>However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex mathematical operations.<n>We present AgentMath, an agent framework that seamlessly integrates language models' reasoning capabilities with code interpreters' computational precision.
  arXiv  Detail & Related papers  (2025-12-23T19:57:49Z)
• Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
  This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
  arXiv  Detail & Related papers  (2025-12-20T12:06:13Z)
• Efficient-Husformer: Efficient Multimodal Transformer Hyperparameter Optimization for Stress and Cognitive Loads [0.0]
  Transformer-based models have gained considerable attention in the field of physiological signal analysis.<n>They leverage long-range dependencies and complex patterns in temporal signals, allowing them to achieve performance superior to traditional RNN and CNN models.<n>We present Efficient-Husformer, a novel Transformer-based architecture for multi-class stress detection.
  arXiv  Detail & Related papers  (2025-11-27T12:02:25Z)
• HeaRT: A Hierarchical Circuit Reasoning Tree-Based Agentic Framework for AMS Design Optimization [13.18012004667103]
  HeaRT is a foundational reasoning engine for automation loops and a first step toward intelligent, adaptive, human-style design optimization.<n>HeaRT consistently demonstrates reasoning accuracy 97% and Pass@1 performance 98% across our 40-circuit benchmark repository.<n>Our experiments show that HeaRT yields 3x faster convergence in both sizing and topology design adaptation tasks.
  arXiv  Detail & Related papers  (2025-11-24T20:11:06Z)
• A Multidisciplinary Design and Optimization (MDO) Agent Driven by Large Language Models [7.509742996975501]
  We present a Multidisciplinary Design and Optimization (MDO) Agent driven by Large Language Models (LLMs)<n>The agent semi-automates the end-to-end workflow by orchestrating three core capabilities: (i) natural-language-driven parametric modeling, (ii) retrieval-augmented generation (RAG) for knowledge-grounded conceptualization, and (iii) intelligent orchestration of engineering software for performance verification and optimization.
  arXiv  Detail & Related papers  (2025-10-06T01:26:55Z)
• ZeroLM: Data-Free Transformer Architecture Search for Language Models [54.83882149157548]
  Current automated proxy discovery approaches suffer from extended search times, susceptibility to data overfitting, and structural complexity.<n>This paper introduces a novel zero-cost proxy methodology that quantifies model capacity through efficient weight statistics.<n>Our evaluation demonstrates the superiority of this approach, achieving a Spearman's rho of 0.76 and Kendall's tau of 0.53 on the FlexiBERT benchmark.
  arXiv  Detail & Related papers  (2025-03-24T13:11:22Z)
• Physics-Constrained Generative Artificial Intelligence for Rapid Takeoff Trajectory Design [0.0]
  This work proposes physics-constrained generative adversarial networks (physicsGAN) to intelligently parameterize the takeoff control profiles of an eVTOL aircraft.<n>The physicsGAN generated only feasible control profiles of power and wing angle in the feasible space with around 98.9% of designs satisfying all constraints.<n>According to the literature review, this is the first physics-constrained generative artificial intelligence enabled by surrogate models.
  arXiv  Detail & Related papers  (2025-01-07T00:15:04Z)
• PearSAN: A Machine Learning Method for Inverse Design using Pearson Correlated Surrogate Annealing [66.27103948750306]
  PearSAN is a machine learning-assisted optimization algorithm applicable to inverse design problems with large design spaces.<n>It uses a Pearson correlated surrogate model to predict the figure of merit of the true design metric.<n>It achieves a state-of-the-art maximum design efficiency of 97%, and is at least an order of magnitude faster than previous methods.
  arXiv  Detail & Related papers  (2024-12-26T17:02:19Z)
• Data-Driven Offline Optimization For Architecting Hardware Accelerators [89.68870139177785]
  We develop a data-driven offline optimization method for designing hardware accelerators, dubbed PRIME. PRIME improves performance upon state-of-the-art simulation-driven methods by about 1.54x and 1.20x, while considerably reducing the required total simulation time by 93% and 99%, respectively. In addition, PRIME also architects effective accelerators for unseen applications in a zero-shot setting, outperforming simulation-based methods by 1.26x.
  arXiv  Detail & Related papers  (2021-10-20T17:06:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.