pith. sign in

arxiv: 2606.09037 · v1 · pith:Z7I5XCJEnew · submitted 2026-06-08 · 💻 cs.AI · cs.MA

A Multi-Agent System for IPMSM Design Optimization via an FEA-AI Hybrid Approach

Jinseong Han , Sunwoong Yang , Namwoo Kang This is my paper

Pith reviewed 2026-06-27 16:50 UTC · model grok-4.3

classification 💻 cs.AI cs.MA
keywords IPMSM design optimizationmulti-agent systemFEA-AI hybrid optimizationuncertainty-aware searchretrieval-augmented generationsurrogate modelinggenetic algorithm
0
0 comments X

The pith

An uncertainty-aware hybrid FEA-AI multi-agent system finds better IPMSM designs than either pure FEA or pure AI search under the same high-fidelity simulation budget.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents an automated multi-agent framework that uses retrieval-augmented generation to define the motor design problem and then runs a genetic-algorithm search in which an AI surrogate handles low-uncertainty candidates while full finite-element analysis corrects high-uncertainty and Pareto-critical points. The Training agent also logs solver failures, applies ANOVA analysis, and triggers resampling to keep the design space valid. A reader would care because the method converts manual, experience-dependent motor optimization into a reproducible workflow that spends the same number of expensive FEA evaluations yet reaches superior objective values with lower and still-decreasing predictive uncertainty.

Core claim

Under a matched high-fidelity FEA budget the hybrid approach achieves better objective performance while maintaining low and further reducible predictive uncertainty, outperforming FEA-only search, which is limited by early budget exhaustion, and AI-only search, which converges to a low-confidence optimum.

What carries the argument

Uncertainty-driven switching rule inside the Optimization agent that routes low-uncertainty candidates to AI-surrogate inference and high-uncertainty or reliability-critical candidates to high-fidelity FEA for correction and retraining.

If this is right

  • The same FEA budget yields designs with higher performance and lower predictive uncertainty than either baseline.
  • Iterative retraining on FEA corrections keeps uncertainty low and further reducible across generations.
  • Solver failures are automatically diagnosed and the design space is adaptively redefined without manual intervention.
  • Targeted FEA on Pareto-front and top-K points produces more reliable fronts than surrogate-only search.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same switching logic could be applied to other expensive multi-physics engineering domains that already use surrogates.
  • If the uncertainty calibration generalizes, the framework could support closed-loop design cycles that reduce human oversight over successive projects.
  • The RAG-based problem-definition step might allow the system to incorporate new design rules or material data without retraining the surrogate from scratch.

Load-bearing premise

The uncertainty estimates from the AI surrogate are sufficiently calibrated that the switching rule reliably decides when the surrogate can be trusted versus when full FEA is required.

What would settle it

A direct comparison on the same IPMSM problem showing that the hybrid Pareto front is no better than an FEA-only run once the uncertainty threshold or the number of FEA corrections is varied.

Figures

Figures reproduced from arXiv: 2606.09037 by Jinseong Han, Namwoo Kang, Sunwoong Yang.

Figure 1
Figure 1. Figure 1: Overall framework of the proposed agent-based FEA–AI hybrid model for IPMSM design optimization. [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Role-assignment and chain-of-thought (CoT) prompt template used for the Design agent. The prompt specifies [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Example interaction in the Design problem definition agent. The agent provides objective-function candidate [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Design-sampling results after Design-agent interaction. (a) Parameterized IPMSM geometry used for variable [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Examples of failed geometries from DOE sampling. Cases (a)–(c) show different invalid shapes caused by [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Example PDF analysis report provided by the agent during the resampling process. The report summarizes [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Autonomous resampling workflow after fail-geometry analysis. The Training agent combines ANOVA-based [PITH_FULL_IMAGE:figures/full_fig_p009_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Deep-ensemble surrogate in the Surrogate training agent. (a) Architecture of the deep-ensemble model [PITH_FULL_IMAGE:figures/full_fig_p010_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Electromagnetic analysis stage in Step 2. The Training agent interacts with the user to set analysis control [PITH_FULL_IMAGE:figures/full_fig_p011_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Inner/outer loop execution strategy in the Optimization agent. The inner loop performs routine evolutionary [PITH_FULL_IMAGE:figures/full_fig_p012_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Uncertainty-aware FEA–AI hybrid evaluator used by the outer loop agent. The evaluator compares predictive [PITH_FULL_IMAGE:figures/full_fig_p013_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Response comparison for an IPMSM saliency question in the RAG study. The user asks why the [PITH_FULL_IMAGE:figures/full_fig_p014_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Per-backbone answer accuracy by question type, without retrieval (No-RAG) and with textbook retrieval [PITH_FULL_IMAGE:figures/full_fig_p015_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Operation of the log-informed resampling loop for the demonstration scenario (objective: iron loss; all [PITH_FULL_IMAGE:figures/full_fig_p016_14.png] view at source ↗
Figure 15
Figure 15. Figure 15: LLM-driven design-space refinement across resampling iterations for the five fail-prone variables. At [PITH_FULL_IMAGE:figures/full_fig_p017_15.png] view at source ↗
Figure 16
Figure 16. Figure 16: FEA–AI hybrid model and GA settings for the IPMSM optimization experiment, covering the deep-ensemble [PITH_FULL_IMAGE:figures/full_fig_p018_16.png] view at source ↗
Figure 17
Figure 17. Figure 17: shows the live predictive uncertainty of every evaluated candidate over the entire optimization, where each panel corresponds to one threshold and the round boundaries (R1–R5) are marked. The figure confirms that the switching threshold strongly determines whether active learning is actually activated during the optimization process. When the threshold is high, as in the 5% and especially 10% cases (panel… view at source ↗
Figure 18
Figure 18. Figure 18: Best objective (iron loss) per evaluation over the full GA process for representative seed 42, under the [PITH_FULL_IMAGE:figures/full_fig_p020_18.png] view at source ↗
Figure 19
Figure 19. Figure 19: Per-round (non-cumulative) FEA-call count for representative seed 42 under the four switching thresholds. [PITH_FULL_IMAGE:figures/full_fig_p021_19.png] view at source ↗
Figure 20
Figure 20. Figure 20: Four-seed average summary of the finally selected design under each switching threshold ( [PITH_FULL_IMAGE:figures/full_fig_p022_20.png] view at source ↗
Figure 21
Figure 21. Figure 21: Comparison of FEA-only GA, AI-surrogate-only GA, and the proposed FEA–AI hybrid GA under a matched [PITH_FULL_IMAGE:figures/full_fig_p023_21.png] view at source ↗
read the original abstract

Interior permanent magnet synchronous motor (IPMSM) design requires balancing conflicting objectives and multi-physics constraints, while modern optimization workflows face three bottlenecks: manual problem setup, high finite element analysis (FEA) cost, and unreliable surrogate-based search in sparse or out-of-distribution regions. To address these limitations, we propose an end-to-end automated IPMSM design optimization framework that integrates retrieval-augmented generation (RAG) for structured problem definition with an uncertainty-aware FEA-AI hybrid optimization pipeline. A Design agent, connected to a motor textbook through RAG, provides domain-knowledge-based options and engineering tips, and compiles an optimization card and a design-of-experiments plan for AI-model training. A Training agent automates electromagnetic FEA, records geometry-validation and solver-failure logs, analyzes failed geometries using ANOVA-based data analysis and LLM reasoning, and invokes a Design Sampling agent to redefine the design space and generate additional samples. An Optimization agent performs GA-based search with uncertainty-driven switching: low-uncertainty candidates are evaluated by AI-surrogate inference, whereas high-uncertainty and reliability-critical Pareto-front or top-K candidates are corrected by high-fidelity FEA and reused for iterative retraining. The framework converts manual, experience-dependent configuration into a reproducible workflow that balances computational cost and prediction reliability. Experimental results under a matched high-fidelity FEA budget show that the proposed hybrid approach achieves better objective performance while maintaining low and further reducible predictive uncertainty, outperforming FEA-only search, which is limited by early budget exhaustion, and AI-only search, which converges to a low-confidence optimum.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript describes a multi-agent system for IPMSM design optimization that uses RAG to automate problem setup from motor textbooks, followed by agents that handle FEA data generation with failure logging and ANOVA analysis, and an optimization agent running GA search with uncertainty-driven switching between AI surrogate evaluations (low-uncertainty points) and high-fidelity FEA (high-uncertainty or Pareto-critical points). The central claim is that, under a matched high-fidelity FEA budget, this hybrid pipeline yields better objective values and lower/reducible predictive uncertainty than either FEA-only search (which exhausts the budget early) or AI-only search (which reaches low-confidence optima).

Significance. If the uncertainty calibration and switching rule are shown to be reliable without introducing systematic bias, the framework would represent a meaningful step toward reproducible, automated multi-physics design workflows that reduce manual configuration effort while controlling computational cost. The explicit integration of LLM agents for both setup and iterative data curation is a distinctive contribution relative to conventional surrogate-assisted optimization pipelines.

major comments (2)
  1. [Abstract and Optimization agent section] Abstract and § on Optimization agent (uncertainty-driven switching): the superiority claim under matched FEA budget depends on the switching rule correctly routing points; however, the manuscript provides no description of the uncertainty model (GP variance, ensemble variance, etc.), no calibration diagnostics (ECE, coverage on held-out or OOD geometries), and no check that miscalibration does not systematically favor surrogate use in regions where prediction error exceeds the reported uncertainty. This is load-bearing for the hybrid-benefit conclusion.
  2. [Experimental results] Experimental results section: the abstract asserts 'better objective performance' and 'low and further reducible predictive uncertainty' but supplies no numerical objective values, no baseline implementation details, no statistical significance tests, and no failure-rate or Pareto-front quality metrics. Without these, the cross-method comparison cannot be evaluated for robustness.
minor comments (2)
  1. [Abstract] The abstract would be strengthened by including at least one or two key quantitative results (e.g., objective improvement percentages or uncertainty reduction) to allow readers to gauge the magnitude of the claimed gains.
  2. [Design agent description] Notation for the 'optimization card' and 'design-of-experiments plan' generated by the Design agent is introduced without a clear definition or example; a short table or pseudocode would improve reproducibility.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback highlighting areas where additional detail and rigor are needed. We address each major comment below and commit to revisions that strengthen the manuscript without altering its core claims.

read point-by-point responses

  1. Referee: [Abstract and Optimization agent section] Abstract and § on Optimization agent (uncertainty-driven switching): the superiority claim under matched FEA budget depends on the switching rule correctly routing points; however, the manuscript provides no description of the uncertainty model (GP variance, ensemble variance, etc.), no calibration diagnostics (ECE, coverage on held-out or OOD geometries), and no check that miscalibration does not systematically favor surrogate use in regions where prediction error exceeds the reported uncertainty. This is load-bearing for the hybrid-benefit conclusion.

    Authors: We agree that the uncertainty model and validation are load-bearing for the hybrid-benefit claim and are insufficiently detailed in the current manuscript. The switching rule relies on ensemble variance from multiple surrogate models, but no calibration or bias analysis is provided. In the revised version we will add a dedicated subsection to the Optimization agent description specifying the ensemble-variance uncertainty estimator, include ECE and coverage-probability diagnostics on held-out and OOD geometries, and present an explicit check that miscalibration does not systematically route high-error points to the surrogate. Supporting figures and text will be added. revision: yes

  2. Referee: [Experimental results] Experimental results section: the abstract asserts 'better objective performance' and 'low and further reducible predictive uncertainty' but supplies no numerical objective values, no baseline implementation details, no statistical significance tests, and no failure-rate or Pareto-front quality metrics. Without these, the cross-method comparison cannot be evaluated for robustness.

    Authors: The full manuscript contains comparative tables and failure logs, yet we acknowledge that numerical values, baseline details, significance tests, and Pareto metrics are not presented with sufficient prominence or completeness for easy evaluation. In the revision we will expand the Experimental results section to display explicit objective values for all three methods, document surrogate architecture, training-set size and GA parameters, report p-values from repeated-run t-tests, and add failure rates together with Pareto-front metrics (hypervolume and spread). revision: yes

Circularity Check

0 steps flagged

No circularity in derivation chain

full rationale

The paper presents an empirical multi-agent framework for IPMSM optimization, with performance claims resting on experimental comparisons of hybrid, FEA-only, and AI-only search under matched high-fidelity FEA budgets. No equations, fitted parameters presented as predictions, self-definitional steps, or load-bearing self-citations appear in the abstract or described workflow; the uncertainty-driven switching and retraining are operational mechanisms validated by observed results rather than by construction from inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available; no explicit free parameters, mathematical axioms, or newly postulated entities are stated.

pith-pipeline@v0.9.1-grok · 5827 in / 1315 out tokens · 33020 ms · 2026-06-27T16:50:00.176925+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

26 extracted references · 1 canonical work pages

  1. [1]

    Research on the performances and parameters of interior pmsm used for electric vehicles.IEEE Transactions on Industrial Electronics, 63(6):3533–3545, 2016

    Xiangdong Liu, Hao Chen, Jing Zhao, and Anouar Belahcen. Research on the performances and parameters of interior pmsm used for electric vehicles.IEEE Transactions on Industrial Electronics, 63(6):3533–3545, 2016

    2016

  2. [2]

    Comparison of induction and pm synchronous motor drives for ev application including design examples.IEEE Transactions on Industry Applications, 48(6):2322–2332, 2012

    Gianmario Pellegrino, Alfredo Vagati, Barbara Boazzo, and Paolo Guglielmi. Comparison of induction and pm synchronous motor drives for ev application including design examples.IEEE Transactions on Industry Applications, 48(6):2322–2332, 2012

    2012

  3. [3]

    Tae-Hyuk Ji, Chan-Ho Kim, Seok-Won Jung, and Sang-Yong Jung. Design method of ipmsm using multi-objective optimization considering mechanical stress for high-speed electric vehicles.Journal of Electrical Engineering & Technology, 19(4):2481–2489, 2024

    2024

  4. [4]

    Multimodal design optimization of v-shaped magnet ipm synchronous machines.IEEE Transactions on Energy Conversion, 33(3):1547–1556, 2018

    Buddhika De Silva Guruwatta Vidanalage, Mohammad Sedigh Toulabi, and Shaahin Filizadeh. Multimodal design optimization of v-shaped magnet ipm synchronous machines.IEEE Transactions on Energy Conversion, 33(3):1547–1556, 2018

    2018

  5. [5]

    Design of a 35 kw permanent magnet synchronous motor for electric vehicle equipped with non-uniform air gap rotor.IEEE Transactions on Industry Applications, 59(1):1184–1198, 2022

    Feng Liu, Xiuhe Wang, and Zezhi Xing. Design of a 35 kw permanent magnet synchronous motor for electric vehicle equipped with non-uniform air gap rotor.IEEE Transactions on Industry Applications, 59(1):1184–1198, 2022

    2022

  6. [6]

    Tomoki Nakata, Masayuki Sanada, Shigeo Morimoto, and Yukinori Inoue. Automatic design of ipmsms using a genetic algorithm combined with the coarse-mesh fem for enlarging the high-efficiency operation area.IEEE Transactions on Industrial Electronics, 64(12):9721–9728, 2017

    2017

  7. [7]

    A survey on large language model based autonomous agents.Frontiers of Computer Science, 18(6):186345, 2024

    Lei Wang, Chen Ma, Xie Feng, Jiahui Zhang, Zeyu Duan, Bowen Zhao, Yuting Wang, Zhendong Zhang, Bo Yang, Qinglong Zheng, et al. A survey on large language model based autonomous agents.Frontiers of Computer Science, 18(6):186345, 2024

    2024

  8. [8]

    Evaluation of different large language model agent frameworks for design engineering tasks

    Alejandro Pradas Gómez, Massimo Panarotto, and Ola Isaksson. Evaluation of different large language model agent frameworks for design engineering tasks. InProceedings of NordDesign 2024: Design in the Era of Digitalization, AI and Augmented Intelligence, pages 693–702, 2024

    2024

  9. [9]

    Generative ai-driven design optimization: Eight key application scenarios.JMST Advances, 7(1):105–111, 2025

    Namwoo Kang. Generative ai-driven design optimization: Eight key application scenarios.JMST Advances, 7(1):105–111, 2025

    2025

  10. [10]

    Meyarivan

    Kalyanmoy Deb, Amrit Pratap, Sameer Agarwal, and T. Meyarivan. A fast and elitist multiobjective genetic algorithm: Nsga-ii.IEEE Transactions on Evolutionary Computation, 6(2):182–197, 2002

    2002

  11. [11]

    Optimal shape design to improve torque characteristics of interior permanent magnet synchronous motor for small electric vehicles.Microsystem Technologies, 31(5):1203–1217, 2025

    Hyeon-Jun Kim and Soo-Whang Baek. Optimal shape design to improve torque characteristics of interior permanent magnet synchronous motor for small electric vehicles.Microsystem Technologies, 31(5):1203–1217, 2025

    2025

  12. [12]

    Topology optimization via machine learning and deep learning: a review.Journal of Computational Design and Engineering, 10(4):1736–1766, 2023

    Seungyeon Shin, Dongju Shin, and Namwoo Kang. Topology optimization via machine learning and deep learning: a review.Journal of Computational Design and Engineering, 10(4):1736–1766, 2023

    2023

  13. [13]

    Multi-objective surrogate optimization of mixed-variable ipm motor design problem with admm-based approach.Optimization and Engineering, pages 1–26, 2025

    Tatsuya Asanuma and Yoshihiro Kanno. Multi-objective surrogate optimization of mixed-variable ipm motor design problem with admm-based approach.Optimization and Engineering, pages 1–26, 2025

    2025

  14. [14]

    Simple and scalable predictive uncertainty estimation using deep ensembles

    Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. Simple and scalable predictive uncertainty estimation using deep ensembles. InAdvances in Neural Information Processing Systems, 2017

    2017

  15. [15]

    Comparative study of different data-driven surrogate models for optimization of synchronous reluctance machine.IEEE Transactions on Industry Applications, 2025

    Yuancong Gong, Andreas Gneiting, Chongshen Zhao, Nejila Parspour, and Hao Chen. Comparative study of different data-driven surrogate models for optimization of synchronous reluctance machine.IEEE Transactions on Industry Applications, 2025

    2025

  16. [16]

    Topology optimization for a spoke-type permanent magnet synchronous motor based on a siamese convolutional network

    Yidan Ma, Zaixin Song, Yongtao Liang, and Jianfu Cao. Topology optimization for a spoke-type permanent magnet synchronous motor based on a siamese convolutional network. In2024 27th International Conference on Electrical Machines and Systems (ICEMS), pages 3346–3351. IEEE, 2024

    2024

  17. [17]

    M. D. McKay, R. J. Beckman, and W. J. Conover. A comparison of three methods for selecting values of input variables in the analysis of output from a computer code.Technometrics, 21(2):239–245, 1979

    1979

  18. [18]

    Survey of hallucination in natural language generation.ACM Computing Surveys, 55(12):248:1– 248:38, 2023

    Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Yejin Bang, Andrea Madotto, and Pascale Fung. Survey of hallucination in natural language generation.ACM Computing Surveys, 55(12):248:1– 248:38, 2023

    2023

  19. [19]

    uttler, Mike Lewis, Wen-tau Yih, Tim Rockt

    Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K"uttler, Mike Lewis, Wen-tau Yih, Tim Rockt"aschel, Sebastian Riedel, and Douwe Kiela. Retrieval-augmented generation for knowledge-intensive nlp tasks. InAdvances in Neural Information Processing Systems, 2020. 25 APREPRINT- JUNE9, 2026

    2020

  20. [20]

    Retrieval augmentation reduces hallucination in conversation

    Kurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela, and Jason Weston. Retrieval augmentation reduces hallucination in conversation. InFindings of the Association for Computational Linguistics: EMNLP 2021, pages 3784–3803, 2021

    2021

  21. [21]

    CRC press, 2009

    Jacek F Gieras.Permanent magnet motor technology: design and applications. CRC press, 2009

    2009

  22. [22]

    The probabilistic relevance framework: BM25 and beyond.Foundations and Trends in Information Retrieval, 3(4):333–389, 2009

    Stephen Robertson and Hugo Zaragoza. The probabilistic relevance framework: BM25 and beyond.Foundations and Trends in Information Retrieval, 3(4):333–389, 2009

    2009

  23. [23]

    Cormack, Charles L

    Gordon V . Cormack, Charles L. A. Clarke, and Stefan Büttcher. Reciprocal rank fusion outperforms Condorcet and individual rank learning methods. InProceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 758–759. ACM, 2009

    2009

  24. [24]

    What uncertainties do we need in bayesian deep learning for computer vision? In Advances in Neural Information Processing Systems, volume 30, 2017

    Alex Kendall and Yarin Gal. What uncertainties do we need in bayesian deep learning for computer vision? In Advances in Neural Information Processing Systems, volume 30, 2017

    2017

  25. [25]

    On the pitfalls of heteroscedastic uncertainty estimation with probabilistic neural networks.arXiv preprint arXiv:2203.09168, 2022

    Maximilian Seitzer, Arash Tavakoli, Dimitrije Antic, and Georg Martius. On the pitfalls of heteroscedastic uncertainty estimation with probabilistic neural networks.arXiv preprint arXiv:2203.09168, 2022

    work page arXiv 2022

  26. [26]

    Uncertainty of measurement: a review of the rules for calculating uncertainty components through functional relationships.The Clinical Biochemist Reviews, 33(2):49, 2012

    Ian Farrance and Richard Frenkel. Uncertainty of measurement: a review of the rules for calculating uncertainty components through functional relationships.The Clinical Biochemist Reviews, 33(2):49, 2012. 26

    2012