Closed-loop AI achieves certifiable engineering design

• URL: http://arxiv.org/abs/2608.21976v1
• Date: Sat, 22 Aug 2026 14:24:58 GMT
• Title: Closed-loop AI achieves certifiable engineering design
• Abstract summary: The AI Engineer is an agentic framework that couples large language models (LLMs) to deterministic engineering backends in a closed loop.<n>It scores each candidate on five dimensions (capacity, steel intensity, unit cost, constructability, and fatigue life) using piecewise-linear functions calibrated on 11 real floating-wind projects.<n>The certified design outperforms the human-optimized TuQiang baseline, reducing steel mass and unit capital cost by 8.1% each while meeting all AIP criteria.
• Score: 4.979561115632364
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agentic AI has automated parts of scientific discovery, including paper generation, expert-level coding, therapeutic proposal, and autonomous experimentation. Complex physical engineering design remains a gap, because candidates must satisfy simultaneous constraints in fluid dynamics, solid mechanics, and structural stability. We introduce The AI Engineer, an agentic framework that couples large language models (LLMs) to deterministic engineering backends in a closed loop: natural-language requirements are converted into design-domain geometry and mesh; topology is optimized with bi-directional evolutionary structural optimization (BESO) coupled to the CalculiX solver; and member sizes are refined with particle swarm optimization (PSO) coupled to Zwind under offshore aero-hydro-servo-elastic load cases. To explore many designs without per-candidate certification cost, an Automated Reviewer scores each candidate on five dimensions (capacity, steel intensity, unit cost, constructability, and fatigue life) using piecewise-linear functions calibrated on 11 real floating-wind projects. Search terminates only when a candidate reaches a composite score $S \ge 85$ (grade A) with no subscore below 60. We validated this gate by submitting the top-scoring design to the China Classification Society (CCS) for Approval in Principle (AIP), which it passed; AIP is thus an external check that the reviewer tracks professional judgment, not the daily objective. The certified design outperforms the human-optimized TuQiang baseline, reducing steel mass and unit capital cost by 8.1% each while meeting all AIP criteria. This verification-closed regime, in which every proposal is judged by deterministic physics and codified limit states, distinguishes The AI Engineer from open-ended generative systems. Remaining limits include detailed design and fabrication-hard constraints.

Related papers

• Accelerated Genetic Programming Hyper-Heuristics for Simulation-Based Scheduling via Agentic AI [42.44812101223683]
  This paper presents a systematic approach using Claude agentic AI on real-world project-scheduling workloads in a high-performance computing environment.<n>Testing runtime reduced from 1,298 seconds to under 200 seconds without changing outputs, saving four million core-hours (NZ$320,000) annually.
  arXiv  Detail & Related papers  (2026-08-19T22:48:46Z)
• CRAFTS: Collaborative Role-Adaptive Fine-Tuning of LLM Agents for Chemical Process Simulation [27.88778816587853]
  CRAFTS mirrors the staged workflow of chemical engineers by decomposing simulation building into bounded subtasks.<n>Fine-tuning is applied to the three schema-critical visual, topology, and specification roles.<n>The resulting VisualGraphIR, TopologyIR, SpecIR, BuildPlan, and SolveReport expose unit, port, thermodynamic, numerical, and execution decisions.
  arXiv  Detail & Related papers  (2026-08-02T16:42:47Z)
• A Lightweight Multi-Agent Framework for Automated Concrete Barrier Design [0.4893345190925178]
  This study proposes a novel framework for automated concrete barrier design using the multi-agent orchestration capabilities of AutoGen.<n> Experimental results demonstrate that the proposed agentic framework achieves over 98% design accuracy, significantly outperforming standalone general-purposes.<n>This finding highlights the potential to substantially reduce computational costs while improving the accessibility of AI-assisted engineering tools for industry applications.
  arXiv  Detail & Related papers  (2026-06-10T13:06:11Z)
• A Multi-Agent System for IPMSM Design Optimization via an FEA-AI Hybrid Approach [4.798313004706817]
  Interior permanent magnet synchronous motor (IPMSM) design requires balancing conflicting objectives and multi-physics constraints.<n>We propose an end-to-end automated IPMSM design optimization framework that integrates retrieval-augmented generation (RAG) for structured problem definition.
  arXiv  Detail & Related papers  (2026-06-08T05:07:46Z)
• VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents [57.240036084348354]
  We introduce VASO, a framework for verification-guided self-evolution of robot skill contracts.<n>VASO verifies logically inconsistent skill contracts, then verifies plans induced by the skill against global and local temporal specifications.<n>On Clearpath Jackal and PX4 quadcopter tasks, VASO reaches 97.2% formal-specification compliance using fewer than 100 optimization samples.
  arXiv  Detail & Related papers  (2026-06-03T20:02:35Z)
• ReqFusion: A Multi-Provider Framework for Automated PEGS Analysis Across Software Domains [0.45880283710344066]
  ReqFusion is an AI-enhanced system that automates the extraction, classification, and analysis of software requirements.<n>The architecture integrates OpenAI GPT, Anthropic Claude, and Groq models to extract functional and non-functional requirements.
  arXiv  Detail & Related papers  (2026-03-24T17:45:40Z)
• 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)
• GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation Protocols [32.505127447635864]
  GENIUS is an AI-agentic workflow that fuses a smart Quantum ESPRESSO knowledge graph with a tiered hierarchy of large language models supervised by a finite-state error-recovery machine.<n> GENIUS translates free-form human-generated prompts into validated input files that run to completion on $approx$80% of 295 diverse benchmarks, where 76% are autonomously repaired, with success decaying exponentially to a 7% baseline.<n>The framework democratizes electronic-structure DFT simulations by intelligently automating protocol generation, validation, and repair, opening large-scale screening and accelerating ICME design loops across academia and industry worldwide.
  arXiv  Detail & Related papers  (2025-12-06T11:28:35Z)
• MAHL: Multi-Agent LLM-Guided Hierarchical Chiplet Design with Adaptive Debugging [30.305211001929496]
  Large Language Models (LLMs) are promising to extend their abilities to 2.5D integration.<n>LLMs face challenges such as flatten design, high validation cost and imprecise parameter optimization.<n>We propose MAHL, a hierarchical LLM-based chiplet design generation framework.
  arXiv  Detail & Related papers  (2025-08-08T05:47:31Z)
• AutoChemSchematic AI: Agentic Physics-Aware Automation for Chemical Manufacturing Scale-Up [2.5875933818780363]
  Current AI systems cannot yet reliably generate critical engineering schematics.<n>We present a closed-loop, physics-aware framework for automated generation of industrially viable PFDs and PIDs.<n>We show that our framework generates simulator-validated process descriptions with high fidelity.
  arXiv  Detail & Related papers  (2025-05-30T13:32:00Z)
• 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)
• Cross-Modality Program Representation Learning for Electronic Design Automation with High-Level Synthesis [45.471039079664656]
  Domain-specific accelerators (DSAs) have gained popularity for applications such as deep learning and autonomous driving. We propose ProgSG, a model that allows interaction between the source code sequence modality and the graph modality in a deep and fine-grained way. We show that ProgSG reduces the RMSE of design performance predictions by up to $22%$, and identifies designs with an average of $1.10times$.
  arXiv  Detail & Related papers  (2024-06-13T22:34:58Z)
• Mechanistic Design and Scaling of Hybrid Architectures [114.3129802943915]
  We identify and test new hybrid architectures constructed from a variety of computational primitives. We experimentally validate the resulting architectures via an extensive compute-optimal and a new state-optimal scaling law analysis. We find MAD synthetics to correlate with compute-optimal perplexity, enabling accurate evaluation of new architectures.
  arXiv  Detail & Related papers  (2024-03-26T16:33:12Z)

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.