arXiv subjects

Soheyl Massoudi

Publications and source records attributed to Soheyl Massoudi.

8 recordsLinked to original sources

arXiv2026

Conditional Flow Matching for ML-Based Inverse Design Problems

Engineering inverse design is often limited by the high computational cost of iterative solvers for optimization problems constrained by partial differential equations (PDEs) and by their sensitivity to initialization. Deep generative models can produce candidate designs without rerunning the simulator at inference time. Generative adversarial networks (GANs) sample in one forward pass, whereas diffusion models require iterative reverse-time integration. In this work, we add conditional flow matching (CFM) to EngiOpt and compare it with a conditional diffusion model and a conditional generative adversarial network (cGAN) on structural (beams2d) and thermal (heatconduction2d) benchmarks from EngiBench using the same downstream optimization protocol. We use cumulative optimality gap (COG) and final optimality gap (FOG) as the primary metrics for evaluating the generated designs as warm starts for gradient-based refinement. On the evaluated EngiOpt implementations and two EngiBench tasks, CFM achieves the lowest measured COG, FOG, maximum mean discrepancy (MMD), and volume-fraction deviation on both tasks. CFM has mean volume-fraction deviations of 0.4% and 1.0% on beams2d and heatconduction2d, respectively, compared with 3.8% and 11.2% for diffusion. At Euler s = 16, CFM achieves 53.2 samples/s on beams2d, about 66 times the measured throughput of the evaluated diffusion baseline using 1000 network evaluations under the same timing protocol, with COG 1.182 +/- 3.126, compared with 1.173 +/- 3.100 for Euler s = 32. Across the two tasks, CFM produces warm starts with lower measured COG than both baselines and uses fewer network evaluations than diffusion.

cs.LG↗

arXiv2026

EngiAI: Capability-Based Evaluation of Tool-Connected LLM Agents for Engineering Design

Engineering-agent systems are proliferating, but differences in tasks, tools, and success criteria make demonstrations difficult to compare and failures difficult to diagnose. We introduce a capability-based evaluation framework for tool-connected engineering agents. The framework separately evaluates workflow execution, retrieval-assisted parameter selection, high-performance computing (HPC) orchestration, and training-code authoring using execution traces and resulting engineering artifacts. We evaluate four LLM backends on the EngiBench Beams2D and Photonics2D problems using EngiAI, a LangGraph reference implementation. On Beams2D, the two proprietary models complete 96-97% of workflow tasks, compared with 55-78% for the two open-source models. Workflows requiring tool-based decision-making perform worse on Photonics2D, reaching 20-53% completion. Indexed retrieval improves parameter selection. For HPC orchestration, Gemini-3-Flash completes every tested pipeline, whereas GPT-5-mini completes 50-70% through the final evaluation step. When the agents must write the training code themselves, they fill small gaps reliably but diverge as larger regions are left open. In the open-synthesis tier, both proprietary models select conditional variational autoencoders instead of the reference conditional Generative Adversarial Network (cGAN); Gemini-3-Flash achieves lower maximum mean discrepancy than the reference in seven of ten Beams2D trials. The results support capability-specific evaluation, with separate scores for distinct skills, rather than assessment through successful end-to-end demonstrations alone. The framework provides common evaluation dimensions for identifying failure mechanisms and structuring comparisons of models, agent architectures, and tool interfaces.

cs.AI↗

arXiv2026

Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers

Large language models (LLMs) typically approach combinatorial optimization as an inference-time procedure, solving each instance separately through sampling, search, or repeated prompting. We ask whether reinforcement learning can instead shift part of this reasoning cost into the weights of a code LLM, so that the model synthesizes a reusable solver for an entire problem family. We study this question on Synergistic Dependency Selection (SDS), a controlled variant of constrained Quadratic Knapsack designed to expose a specific failure mode: local signals and strict feasibility constraints make greedy heuristics attractive but unreliable. Under identical scaffolding, Best-of-64 base-model sampling saturates at an approximately 28.7% gap to the global Virtual Best Solver (VBS); code audits show that the base model often retrieves Simulated Annealing templates but misimplements the Metropolis acceptance rule. We fine-tune Qwen2.5-Coder-14B-Instruct with Group Relative Policy Optimization (GRPO) using a feasibility-gated reward and light structural scaffolding. The resulting policy converges to a constraint-aware Simulated Annealing template in 99.8% of feasible SDS outputs, achieves a 5.0% gap to that VBS, and is 91 times cheaper in post-generation execution/search cost than cumulative Best-of-64 evaluation. A compile-once check shows that one best frozen solver per seed remains highly competitive when reused unchanged across the SDS test set, while an additional-domain evaluation on Job Shop Scheduling provides narrower but positive evidence that the scaffold transfers beyond SDS. Negative ablations reveal the limits of this recipe: standard stabilizers degrade performance, a soft feasibility gate fails, and results remain sensitive to reward normalization and domain-specific design choices.

cs.LG↗

arXiv2026

GLUE: Coordinating Pre-Trained Generative Models for System-Level Design

Engineering complex systems (aircraft, buildings, vehicles) requires coordinating geometric and performance couplings across subsystems. As generative models proliferate for specialized domains, a key research gap is how to coordinate frozen, pre-trained submodels to generate full-system designs that are feasible, diverse, and high-performing. We introduce GLUE, which orchestrates pre-trained, frozen generators while enforcing system-level feasibility, optimality, and diversity. Compatible models must be end-to-end differentiable with a smooth, well-behaved latent-to-output mapping. We propose and benchmark (i) data-driven GLUE models trained on pre-generated system-level designs and (ii) a data-free GLUE model trained on a differentiable geometry layer. On a UAV design problem with five coupling constraints, we find that data-driven approaches yield diverse, high-performing designs but require large datasets to satisfy constraints reliably. The data-free approach is competitive with Bayesian optimization and gradient-based optimization in performance and feasibility while training a full generative model in only ~10 min on an RTX 4090 GPU, requiring more than two orders of magnitude fewer geometry evaluations and FLOPs than the data-driven method. We identify equality constraint satisfaction as a key difficulty and remaining limitation, and ablate approaches that improve this for the data-free approach. As a first step toward scaling generative design to complex, real-world engineering systems, this work explores how unmodified, domain-informed submodels can be integrated into a modular generative workflow.

cs.CE↗

arXiv2025

Agentic Large Language Models for Conceptual Systems Engineering and Design

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.

cs.AI↗

arXiv2025

EngiBench: A Framework for Data-Driven Engineering Design Research

Engineering design optimization seeks to automatically determine the shapes, topologies, or parameters of components that maximize performance under given conditions. This process often depends on physics-based simulations, which are difficult to install, computationally expensive, and require domain-specific expertise. To mitigate these challenges, we introduce EngiBench, the first open-source library and datasets spanning diverse domains for data-driven engineering design. EngiBench provides a unified API and a curated set of benchmarks -- covering aeronautics, heat conduction, photonics, and more -- that enable fair, reproducible comparisons of optimization and machine learning algorithms, such as generative or surrogate models. We also release EngiOpt, a companion library offering a collection of such algorithms compatible with the EngiBench interface. Both libraries are modular, letting users plug in novel algorithms or problems, automate end-to-end experiment workflows, and leverage built-in utilities for visualization, dataset generation, feasibility checks, and performance analysis. We demonstrate their versatility through experiments comparing state-of-the-art techniques across multiple engineering design problems, an undertaking that was previously prohibitively time-consuming to perform. Finally, we show that these problems pose significant challenges for standard machine learning methods due to highly sensitive and constrained design manifolds.

cs.CE↗

arXiv2022

ARRID: ANN-based Rotordynamics for Robust and Integrated Design

The purpose of this study is to introduce ANN-based software for the fast evaluation of rotordynamics in the context of robust and integrated design. It is based on a surrogate model made of ensembles of artificial neural networks running in a Bokeh web application. The use of a surrogate model has sped up the computation by three orders of magnitude compared to the current models. ARRID offers fast performance information, including the effect of manufacturing deviations. As such, it helps the designer to make optimal design choices early in the design process. The designer can manipulate the parameters of the design and the operating conditions to obtain performance information in a matter of seconds.

cs.NE↗

arXiv2017

Quasi-Elastic Neutrino Reactions on Carbon and Lead Nuclei

We examine neutral-current quasi-elastic neutrino-nucleus reactions on $^{12}$C and $^{208}$Pb targets. We use the relativistic mean field theory approach to describe the nuclear dynamics. We compute the cross sections for the scattering of 150-MeV, 500-MeV and 1000-MeV neutrinos on a $^{12}$C target and study the effect of the strange-quark content of the nucleon which appears in these reactions via the isoscalar weak current. We compare our results with the data of the MiniBooNE experiment for mineral oil (CH$_2$). We also calculate the cross section for the quasi-elastic neutron knockout reaction of 20 to 60-MeV neutrinos on a $^{208}$Pb target which is relevant to plans to use lead as a target material in future supernova neutrino detectors.

nucl-th↗