Engineering Reasoning and Instruction (ERI) Benchmark: A Large Taxonomy-driven Dataset for Foundation Models and Agents

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Naser, MZ, Awwad, Ahmad Bani, McCreery, Zoie, Eissa, Radwa, Naser, Ahmad, Cusatis, Gianluca, Metcalf, Andrew, Madathil, Kapil, Abdalla, Jamal, Kodur, Venkatesh, Saeb, Mohammad Reza
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914364391424000
author Naser, MZ
Awwad, Ahmad Bani
McCreery, Zoie
Eissa, Radwa
Naser, Ahmad
Cusatis, Gianluca
Metcalf, Andrew
Madathil, Kapil
Abdalla, Jamal
Kodur, Venkatesh
Saeb, Mohammad Reza
author_facet Naser, MZ
Awwad, Ahmad Bani
McCreery, Zoie
Eissa, Radwa
Naser, Ahmad
Cusatis, Gianluca
Metcalf, Andrew
Madathil, Kapil
Abdalla, Jamal
Kodur, Venkatesh
Saeb, Mohammad Reza
contents The Engineering Reasoning and Instruction (ERI) benchmark is a taxonomy-driven instruction dataset designed to train and evaluate engineering-capable large language models (LLMs) and agents. This dataset spans nine engineering fields (namely: civil, mechanical, electrical, chemical, environmental, aerospace, materials, fire, and industrial engineering) and 55 subdomains, and is crossed with seven intent types (i.e., definition, explanation, calculation, comparison, design/synthesis, troubleshooting, and code-related) and three difficulty tiers (undergraduate, graduate, and professional), yielding 57,750 records with field/subdomain/type/difficulty metadata and solution formatting. We examined ERI via seven LLMs and report a statistically significant three-tier performance structure, with frontier models (GPT-5, Claude Sonnet 4, DeepSeek V3.1) achieving mean scores above 4.30 on a five-point scale, while mid-tier and smaller models exhibited progressively higher failure rates and steeper performance degradation on graduate-level questions. To address circularity concerns inherent in LLM benchmarks, we developed a convergent validation protocol that leverages cross-provider independence, multi-judge averaging, and frontier-model agreement analysis to empirically bound hallucination risk to 1.7%. ERI is released with taxonomy specifications, validation scripts, and an evaluation harness to enable reproducible comparisons and regression testing for instruction tuning, routing, retrieval-augmented evaluation, and agentic tool-use workflows in engineering settings.
format Preprint
id arxiv_https___arxiv_org_abs_2603_02239
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Engineering Reasoning and Instruction (ERI) Benchmark: A Large Taxonomy-driven Dataset for Foundation Models and Agents
Naser, MZ
Awwad, Ahmad Bani
McCreery, Zoie
Eissa, Radwa
Naser, Ahmad
Cusatis, Gianluca
Metcalf, Andrew
Madathil, Kapil
Abdalla, Jamal
Kodur, Venkatesh
Saeb, Mohammad Reza
Artificial Intelligence
Software Engineering
The Engineering Reasoning and Instruction (ERI) benchmark is a taxonomy-driven instruction dataset designed to train and evaluate engineering-capable large language models (LLMs) and agents. This dataset spans nine engineering fields (namely: civil, mechanical, electrical, chemical, environmental, aerospace, materials, fire, and industrial engineering) and 55 subdomains, and is crossed with seven intent types (i.e., definition, explanation, calculation, comparison, design/synthesis, troubleshooting, and code-related) and three difficulty tiers (undergraduate, graduate, and professional), yielding 57,750 records with field/subdomain/type/difficulty metadata and solution formatting. We examined ERI via seven LLMs and report a statistically significant three-tier performance structure, with frontier models (GPT-5, Claude Sonnet 4, DeepSeek V3.1) achieving mean scores above 4.30 on a five-point scale, while mid-tier and smaller models exhibited progressively higher failure rates and steeper performance degradation on graduate-level questions. To address circularity concerns inherent in LLM benchmarks, we developed a convergent validation protocol that leverages cross-provider independence, multi-judge averaging, and frontier-model agreement analysis to empirically bound hallucination risk to 1.7%. ERI is released with taxonomy specifications, validation scripts, and an evaluation harness to enable reproducible comparisons and regression testing for instruction tuning, routing, retrieval-augmented evaluation, and agentic tool-use workflows in engineering settings.
title Engineering Reasoning and Instruction (ERI) Benchmark: A Large Taxonomy-driven Dataset for Foundation Models and Agents
topic Artificial Intelligence
Software Engineering
url https://arxiv.org/abs/2603.02239