cs.LGNov 3, 2026

SteelAgent: LLM-Orchestrated, Physics-Informed Steel Property Prediction with Audited Generalization and Calibrated Uncertainty

Authors: Aleksandr Volkov, Roman Sultimov, Mikhail Kuzin, Yury Maximov

Abstract

Steel property models can perform well on random test splits even when they extrapolate poorly to unfamiliar alloys. SteelAgent couples metallurgical descriptors and machine-learning models with a language-model interface for property prediction, uncertainty reporting and inverse design. We examine how the choice of held-out unit changes the conclusions drawn from SteelBench tensile-strength evaluations. For gradient boosting, pooled out-of-fold R2R^2 fell from 0.859 on a random split to 0.113 when steel families were held out. Empirical coverage of nominal 90% prediction intervals ranged from 91.0% under random splitting to 37.6% on held-out sources. The effect of physics-derived features depended on the evaluation. They increased gradient-boosting R2R^2 by 0.2534 in a 17-family holdout analysis and decreased it by 0.358 in a separate four-grade laboratory analysis. We report group-level errors and a synthetic regression experiment illustrating how calibration can deteriorate on held-out groups. These results motivate reporting the evaluation population alongside a property estimate or compliance score.

Figures & tables

Explore similar work

Nov 2, 2026

Quantifying out-of-distribution data severity with Wasserstein distances: benchmarking large language models for alloy property prediction

General-purpose Large Language Models (LLMs) increasingly rival domain-specific pipelines on scientific prediction, but their performance under distribution shift is untested. Across six alloy and crystal-structure datasets, we benchmark LLMs against traditional, BERT-based, TabPFN, and text-regression baselines under random cross-validation and six out-of-distribution (OOD) protocols shifting input and target distributions, with severity quantified via a standardized Wasserstein distance. We isolate the LLM's advantage over k-nearest-neighbor (k-NN) retrieval: it beats k-NN on all eight tasks at a fixed 5% reference budget, on seven of eight when independently optimized, and in 72.5% of 120 OOD task--protocol configurations against an optimized baseline. No model family is uniformly best; the LLM is often strongest under severe shift, and error increases with target-space but not representation-space severity. Self-reported LLM confidence tracks both shift and error, more consistently than a density-only control from the same retrieved samples, and a matched-cohort check finds no substantial evidence of memorization.
Aug 5, 2026

Distribution-Free Conformal Prediction for Steel Fatigue Strength: Marginal Validity Is Not Enough

Predicting fatigue failure in steel components experimentally is costly because it requires testing across multiple compositions and processing conditions. This has spurred research on data-driven prediction models. Studies using the NIMS MatNavi steel fatigue dataset often report high point-prediction accuracy but rely on aggregate error metrics, leaving uncertainty about the reliability of individual predictions and whether accuracy is consistent across the fatigue-strength spectrum. This paper is the first to apply conformal prediction to steel fatigue strength, comparing five interval-construction methods across 50 independent data splits and distinguishing marginal coverage from coverage within specific sub-regions of the predicted property. A gradient-boosting point model achieves an R^2 of 0.976 +/- 0.009 and a mean absolute error of 18.3 +/- 2.3 MPa. Split-conformal prediction provides valid marginal coverage (0.918) but drops to 0.755 in the highest-strength quartile, where design margins are most critical, a pattern also observed with a Gaussian process baseline. A cross-fitted, normalized conformal method restores near-uniform coverage across all quartiles (0.869-0.938) without a significant increase in interval width, by scaling the interval based on a cross-fitted estimate of local prediction difficulty rather than using a single global width. Diagnostic analysis traces the residual gap in the highest-strength quartile to elevated residual variance (2.7x the pooled Q1-Q3 level) rather than a systematic bias, situating the shortfall against a proven distribution-free limit on exact conditional coverage. Marginal coverage claims for ML-based fatigue-strength predictions can conceal systematic unreliability precisely where engineering decisions are most risky; therefore, conditional coverage should be routinely assessed alongside marginal coverage.
Mar 24, 2026

Multitask-Informed Prior for In-Context Learning on Tabular Data: Application to Steel Property Prediction

Accurate prediction of mechanical properties of steel during hot rolling processes, such as Thin Slab Direct Rolling (TSDR), remains challenging due to complex interactions among chemical compositions, processing parameters, and resultant microstructures. Traditional empirical and experimental methodologies, while effective, are often resource-intensive and lack adaptability to varied production conditions. Moreover, most existing approaches do not explicitly leverage the strong correlations among key mechanical properties, missing an opportunity to improve predictive accuracy through multitask learning. To address this, we present a multitask learning framework that injects multitask awareness into the prior of TabPFN--a transformer-based foundation model for in-context learning on tabular data--through novel fine-tuning strategies. Originally designed for single-target regression or classification, we augment TabPFN's prior with two complementary approaches: (i) target averaging, which provides a unified scalar signal compatible with TabPFN's single-target architecture, and (ii) task-specific adapters, which introduce task-specific supervision during fine-tuning. These strategies jointly guide the model toward a multitask-informed prior that captures cross-property relationships among key mechanical metrics. Extensive experiments on an industrial TSDR dataset demonstrate that our multitask adaptations outperform classical machine learning methods and recent state-of-the-art tabular learning models across multiple evaluation metrics. Notably, our approach enhances both predictive accuracy and computational efficiency compared to task-specific fine-tuning, demonstrating that multitask-aware prior adaptation enables foundation models for tabular data to deliver scalable, rapid, and reliable deployment for automated industrial quality control and process optimization in TSDR.