{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T15:00:32Z","timestamp":1777388432173,"version":"3.51.4"},"reference-count":25,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:00:00Z","timestamp":1777334400000},"content-version":"vor","delay-in-days":117,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Understanding Classical Chinese remains a major challenge in Chinese education, especially in the National College Entrance Examination (NCEE). Although large language models (LLMs) exhibit strong reasoning capabilities, their performance on exam\u2010style Classical Chinese questions still suffers from instability and limited accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose a multiagent reasoning framework based on LLMs for Classical Chinese question answering. For each question type, standardized reasoning procedures are defined, and specialized agents are trained for subtasks including word interpretation, grammatical analysis, translation, and semantic summarization. A two\u2010round reasoning mechanism, consisting of an initial response followed by refinement using standard answers, is introduced to enhance consistency and robustness.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experiments on Gaokao\u2010style Classical Chinese questions demonstrate that the proposed framework achieves higher accuracy and greater reasoning stability than single\u2010agent systems and general\u2010purpose LLMs. In objective tasks, it outperforms strong Chinese\u2010oriented models such as Qwen\u2010Max and Baichuan\u20104 by up to 6.8%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The proposed multiagent framework improves both the interpretability and reliability of LLM\u2010based Classical Chinese understanding. It shows strong potential for applications in intelligent tutoring systems, curriculum support, and cognitive modeling of human\u2010like reasoning in educational contexts.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1155\/int\/8987020","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T09:41:19Z","timestamp":1777369279000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multiagent Reasoning Framework for Classical Chinese Question Answering With Large Language Models"],"prefix":"10.1155","volume":"2026","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1874-7458","authenticated-orcid":false,"given":"Qing","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Nong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuemei","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yajie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongmeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulin","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,4,28]]},"reference":[{"key":"e_1_2_13_1_2","doi-asserted-by":"publisher","DOI":"10.1145\/3551637"},{"key":"e_1_2_13_2_2","first-page":"353","article-title":"Research on the Evaluation of the Classical Chinese Difficulty in the Compulsory Education Stage","author":"Ma K.","year":"2022","journal-title":"IEEE"},{"key":"e_1_2_13_3_2","volume-title":"Introduction to Classical Chinese","author":"Vogelsang K.","year":"2021"},{"key":"e_1_2_13_4_2","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2021.lchange-1.1","volume-title":"Time-Aware Ancient Chinese Text Translation and Inference","author":"Chang E.","year":"2021"},{"key":"e_1_2_13_5_2","first-page":"1","article-title":"Exploring the Limits of Transfer Learning With a Unified Text-to-Text Transformer","volume":"21","author":"Raffel C.","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_13_6_2","unstructured":"WangD. LinL. ZhaoZ.et al. Evahan2023: Overview of the First International Ancient Chinese Translation Bakeoff 2023 1\u201314."},{"key":"e_1_2_13_7_2","volume-title":"GPT-4 Technical Report","author":"OpenAI","year":"2023"},{"key":"e_1_2_13_8_2","volume-title":"Code Llama: Open Foundation Models for Code","author":"Roziere B.","year":"2023"},{"key":"e_1_2_13_9_2","volume-title":"Sikugpt: A Generative Pretrained Model for Intelligent Information Processing of Ancient Texts from the Perspective of Digital Humanities","author":"Chang L.","year":"2023"},{"key":"e_1_2_13_10_2","volume-title":"A Large Language Model-Based Computational Approach to Improve Identity-Related Write-Ups","author":"Doboli A.","year":"2023"},{"key":"e_1_2_13_11_2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-02934-0_25","volume-title":"CNN-BiLSTM-CRF Model for Term Extraction in Chinese Corpus","author":"Han X.","year":"2018"},{"key":"e_1_2_13_12_2","first-page":"289","volume-title":"BERT-Based Named Entity Recognition in Chinese Twenty-Four Histories","author":"Yu P.","year":"2020"},{"key":"e_1_2_13_13_2","volume-title":"ChatGLM: A Family of Large Language Models From GLM-130B to GLM-4 all Tools","author":"Glm T.","year":"2024"},{"key":"e_1_2_13_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2025.104286"},{"key":"e_1_2_13_15_2","volume-title":"AC-Eval: Evaluating Ancient Chinese Language Understanding in Large Language Models","author":"Wei Y.","year":"2024"},{"key":"e_1_2_13_16_2","volume-title":"Tonggu: Mastering Classical Chinese Understanding With Knowledge-Grounded Large Language Models","author":"Cao J.","year":"2024"},{"key":"e_1_2_13_17_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-23904-0"},{"key":"e_1_2_13_18_2","volume-title":"EduChat: A Large-Scale Language Model-Based Chatbot System for Intelligent Education","author":"Dan Y.","year":"2023"},{"key":"e_1_2_13_19_2","volume-title":"A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","author":"Huang Y.","year":"2023"},{"key":"e_1_2_13_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/s44217-025-00424-7"},{"key":"e_1_2_13_21_2","volume-title":"Mixture-Of-Agents Enhances Large Language Model Capabilities","author":"Wang J.","year":"2024"},{"key":"e_1_2_13_22_2","volume-title":"ChatGLM: A Family of Large Language Models From GLM-130B to GLM-4 all Tools","author":"Zeng A.","year":"2024"},{"key":"e_1_2_13_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3538610"},{"key":"e_1_2_13_24_2","volume-title":"LLaMAFactory: Unified Efficient Fine-Tuning of 100+ Language Models","author":"Zheng Y.","year":"2024"},{"key":"e_1_2_13_25_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29861"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/8987020","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/8987020","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/8987020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T09:41:27Z","timestamp":1777369287000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/8987020"}},"subtitle":[],"editor":[{"given":"Richard","family":"Murray","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":25,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1155\/int\/8987020"],"URL":"https:\/\/doi.org\/10.1155\/int\/8987020","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-10-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"8987020"}}