{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T02:00:14Z","timestamp":1777773614475,"version":"3.51.4"},"reference-count":48,"publisher":"ASME International","issue":"7","license":[{"start":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:00:00Z","timestamp":1777420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Engineering documents, such as design rule books and technical requirements, play a critical role in helping engineers ensure that their designs meet specified standards. Quickly retrieving and reasoning over such documents is essential for efficient engineering workflows. Recent advances in large language models (LLMs) and generative AI make it possible to automatically interpret and reason over complex engineering documents. However, engineering covers many distinct and highly specialized subdomains. Because general-purpose LLMs such as GPT or Gemini are not trained or fine-tuned on these domains, their performance on domain-specific reasoning remains limited. It is impractical to curate dedicated datasets for every engineering subdomain, which would be required for both fine-tuning and building reliable retrieval-augmented generation frameworks. Therefore, it is crucial to develop a principled agent-based design paradigm that can be instantiated for specific engineering documentation tasks under data-scarce conditions. To address this, we propose an agent-based framework that leverages existing LLM capabilities through specialized agents coordinated by a routing mechanism, achieving a scalable and fully automated workflow. We evaluate our framework on DesignQA as a representative case study and show that it consistently outperforms baseline methods. Moreover, the results highlight its potential to generalize across diverse engineering requirements. In future work, we plan to extend this framework to additional engineering domains and explore more advanced agent strategies.<\/jats:p>","DOI":"10.1115\/1.4071111","type":"journal-article","created":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:55:04Z","timestamp":1770918904000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":0,"title":["Agent-Based Framework for Engineering Document Comprehension With Large Language Models"],"prefix":"10.1115","volume":"26","author":[{"given":"Haoyang","family":"Xie","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/03efmqc40","id-type":"ROR","asserted-by":"publisher"}],"name":"Arizona State University School of Computing and Augmented Intelligence, , 699 S Mill Ave, , \u00a0","place":["Tempe, AZ, 85281"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Ju","sequence":"additional","affiliation":[{"name":"Arizona State University School of Computing and Augmented Intelligence, , 699 S Mill Ave, , \u00a0","place":["Tempe, AZ, 85281"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"33","published-online":{"date-parts":[[2026,4,29]]},"reference":[{"issue":"4","key":"2026042913242981900_CIT0001","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1080\/09544820410001697154","article-title":"Knowledge Management in Engineering Design: Personalization and Codification","volume":"15","author":"McMahon","year":"2004","journal-title":"J. Eng. Design"},{"key":"2026042913242981900_CIT0002","unstructured":"Gaither, A.\n          , 2021, \u201cVehicle Dynamics on an Electric Formula SAE Racecar,\u201d Ph.D. thesis, Massachusetts Institute of Technology, Cambridge, MA."},{"key":"2026042913242981900_CIT0003","unstructured":"Stenholm, D.\n          , 2016, \u201cEngineering Knowledge-Support for Effective Reuse of Experience-Based Codified Knowledge in Incremental Product Development,\u201d Master\u2019s thesis, Chalmers Tekniska H\u00f6gskola, Gothenburg, Sweden."},{"key":"2026042913242981900_CIT0004","author":"Xie","year":"2025"},{"key":"2026042913242981900_CIT0005","first-page":"1877","article-title":"Language Models Are Few-Shot Learners","author":"Brown"},{"key":"2026042913242981900_CIT0006","author":"Team","year":"2023"},{"key":"2026042913242981900_CIT0007","author":"Bai","year":"2023"},{"key":"2026042913242981900_CIT0008","author":"Liu","year":"2024"},{"key":"2026042913242981900_CIT0009","doi-asserted-by":"crossref","article-title":"Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey","author":"Song","DOI":"10.18653\/v1\/2025.findings-emnlp.1379"},{"key":"2026042913242981900_CIT0010","first-page":"000233","article-title":"Fine-Tuning Large Language Models for Scientific Text Classification: A Comparative Study","author":"Rostam"},{"key":"2026042913242981900_CIT0011","author":"Jeong","year":"2024"},{"key":"2026042913242981900_CIT0012","article-title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","author":"Lewis"},{"key":"2026042913242981900_CIT0013","author":"Gao","year":"2023"},{"key":"2026042913242981900_CIT0014","author":"Weller","year":"2025"},{"key":"2026042913242981900_CIT0015","author":"Luo","year":"2025"},{"key":"2026042913242981900_CIT0016","article-title":"Large language model based multi-agents: a survey of progress and challenge","author":"Guo"},{"key":"2026042913242981900_CIT0017","first-page":"4171","article-title":"Bert: Pre-Training of Deep Bidirectional Transformers for Language Understanding","author":"Devlin"},{"key":"2026042913242981900_CIT0018","doi-asserted-by":"crossref","article-title":"A Survey on In-context Learning","author":"Dong","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"2026042913242981900_CIT0019","author":"Gu","year":"2024"},{"issue":"2","key":"2026042913242981900_CIT0020","doi-asserted-by":"publisher","first-page":"021009","DOI":"10.1115\/1.4067333","article-title":"Designqa: A Multimodal Benchmark for Evaluating Large Language Models\u2019 Understanding of Engineering Documentation","volume":"25","author":"Doris","year":"2025","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2026042913242981900_CIT0021","first-page":"502","article-title":"Pure: A Dataset of Public Requirements Documents","author":"Ferrari"},{"key":"2026042913242981900_CIT0022","doi-asserted-by":"crossref","article-title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","author":"Dasigi","DOI":"10.18653\/v1\/2021.naacl-main.365"},{"key":"2026042913242981900_CIT0023","doi-asserted-by":"crossref","article-title":"Zeroscrolls: A Zero-Shot Benchmark for Long Text Understanding","author":"Shaham","DOI":"10.18653\/v1\/2023.findings-emnlp.536"},{"key":"2026042913242981900_CIT0024","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.emnlp-main.925","article-title":"Can Pre-Trained Vision and Language Models Answer Visual Information-Seeking Questions?","author":"Chen","year":"2023"},{"key":"2026042913242981900_CIT0025","first-page":"2507","article-title":"Learn to Explain: Multimodal Reasoning Via Thought Chains for Science Question Answering","author":"Lu"},{"key":"2026042913242981900_CIT0026"},{"issue":"3","key":"2026042913242981900_CIT0027","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3764579","article-title":"Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey","volume":"58","author":"Ling","year":"2023","journal-title":"ACM Comput. Surveys"},{"issue":"2","key":"2026042913242981900_CIT0028","doi-asserted-by":"publisher","first-page":"021010","DOI":"10.1115\/1.4067389","article-title":"Integrating Graph Retrieval-Augmented Generation With Large Language Models for Supplier Discovery","volume":"25","author":"Li","year":"2025","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"2","key":"2026042913242981900_CIT0029","doi-asserted-by":"publisher","first-page":"021001","DOI":"10.1115\/1.4066773","article-title":"A Conceptual Design Method Based on Concept\u2013Knowledge Theory and Large Language Models","volume":"25","author":"Chen","year":"2025","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"1","key":"2026042913242981900_CIT0030","doi-asserted-by":"publisher","first-page":"011002","DOI":"10.1115\/1.4069499","article-title":"ConceptVis: Exploring and Visualizing Design Concepts With Large Language Models Using Interactive Knowledge Graph","volume":"26","author":"Duan","year":"2026","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2026042913242981900_CIT0031","author":"Fallahpour","year":"2025"},{"key":"2026042913242981900_CIT0032","article-title":"SWE-Agent: Agent-Computer Interfaces Enable Automated Software Engineering","author":"Yang"},{"issue":"2","key":"2026042913242981900_CIT0033","doi-asserted-by":"publisher","first-page":"021012","DOI":"10.1115\/1.4067388","article-title":"Elicitron: A Large Language Model Agent-Based Simulation Framework for Design Requirements Elicitation","volume":"25","author":"Ataei","year":"2025","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2026042913242981900_CIT0034"},{"key":"2026042913242981900_CIT0035","doi-asserted-by":"crossref","article-title":"BLEU: A Method for Automatic Evaluation of Machine Translation","author":"Papineni","DOI":"10.3115\/1073083.1073135"},{"key":"2026042913242981900_CIT0036","first-page":"74","article-title":"Rouge: A Package for Automatic Evaluation of Summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"2026042913242981900_CIT0037","doi-asserted-by":"crossref","article-title":"Sentence-BERT: Sentence Embeddings Using Siamese BERT-Networks","author":"Reimers","DOI":"10.18653\/v1\/D19-1410"},{"key":"2026042913242981900_CIT0038","article-title":"Bertscore: Evaluating Text Generation With Bert","author":"Zhang"},{"key":"2026042913242981900_CIT0039","author":"Adhikari","year":"2019"},{"key":"2026042913242981900_CIT0040","author":"Chen","year":"2019"},{"key":"2026042913242981900_CIT0041","author":"Wang","year":"2024"},{"key":"2026042913242981900_CIT0042","author":"Kakarla","year":"2025"},{"key":"2026042913242981900_CIT0043","article-title":"Attention Is All You Need","author":"Vaswani","year":"2017"},{"key":"2026042913242981900_CIT0044","author":"Singer-Vine","year":"2025"},{"key":"2026042913242981900_CIT0045","article-title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","author":"Rein"},{"key":"2026042913242981900_CIT0046","first-page":"9556","article-title":"Mmmu: A Massive Multi-Discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","author":"Yue"},{"key":"2026042913242981900_CIT0047","author":"OpenAI","year":"2025"},{"key":"2026042913242981900_CIT0048","author":"Liu","year":"2022"}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/26\/7\/071003\/7591578\/jcise-25-1521.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/26\/7\/071003\/7591578\/jcise-25-1521.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T17:24:34Z","timestamp":1777483474000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/26\/7\/071003\/1230570\/Agent-Based-Framework-for-Engineering-Document"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,29]]},"references-count":48,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4071111","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"value":"1530-9827","type":"print"},{"value":"1944-7078","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,29]]},"article-number":"071003"}}