{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T02:52:56Z","timestamp":1777949576105,"version":"3.51.4"},"reference-count":29,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T00:00:00Z","timestamp":1777766400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Young Talent Cultivation Fund of CIAE","award":["25799"],"award-info":[{"award-number":["25799"]}]},{"name":"SASTIND Stable Support Scientific Research Project","award":["24862"],"award-info":[{"award-number":["24862"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Nuclear Fuel Reprocessing literature contains critical experimental parameters, safety information, theoretical relations, and process data that are highly heterogeneous and subject to strict logical constraints. Manually interpreting complex charts and handling tedious database schema mappings imposes a high cognitive load on experts. Although existing Large Multimodal Models (LMMs) have demonstrated strong potential in information extraction, they often face engineering bottlenecks\u2014such as poor structural compliance and a tendency to confuse entity logic\u2014when dealing with domain databases containing complex foreign key constraints. To address this, we propose GenForge, a schema-aware extraction framework. By taking the target database schema as an explicit constraint, GenForge achieves automatic task decomposition and formatting self-correction via a \u201cGeneration\u2013Execution\u2013Reflection\u2013Reforging\u201d iterative loop. Additionally, a Local ID mechanism is introduced to ensure data lineage consistency. We evaluated GenForge on four internal evaluation corpora from nuclear fuel reprocessing literature, each aligned with a distinct database schema: Safety Event and Causal Context Extraction Schema, Property-Condition Data Extraction Schema, Model-Parameter Association Schema, and Process Topology and Stream Mapping Schema. On the independent test set, GenForge achieved 88.0% precision, 83.0% recall, and a 98.6% Schema Compliance Rate (SCR). These results indicate that GenForge, as an expert-assisted framework, reduces the need for manual JSON debugging and supports practical schema-constrained knowledge extraction under four schema-specific evaluation settings within the Nuclear Fuel Reprocessing domain.<\/jats:p>","DOI":"10.3390\/info17050441","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T01:12:09Z","timestamp":1777857129000},"page":"441","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GenForge: An LMM Agent Framework for Intelligent Knowledge Extraction from Nuclear Fuel Reprocessing Literature"],"prefix":"10.3390","volume":"17","author":[{"given":"Hengfei","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science, University of South China, Hengyang 421001, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Yu","sequence":"additional","affiliation":[{"name":"China Institute of Atomic Energy, Beijing 102413, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanzheng","family":"Xin","sequence":"additional","affiliation":[{"name":"China Institute of Atomic Energy, Beijing 102413, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zonghui","family":"Lu","sequence":"additional","affiliation":[{"name":"China Institute of Atomic Energy, Beijing 102413, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuangjian","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingting","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Mathematics, Sichuan University, Chengdu 610065, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoan","family":"Ye","sequence":"additional","affiliation":[{"name":"China Institute of Atomic Energy, Beijing 102413, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helin","family":"Gong","sequence":"additional","affiliation":[{"name":"SJTU Paris Elite Institute of Technology, Shanghai Jiao Tong University, Shanghai 200240, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5879-5980","authenticated-orcid":false,"given":"Tao","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of South China, Hengyang 421001, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"113138","DOI":"10.1016\/j.nucengdes.2024.113138","article-title":"Treatment of spent radioactive organic solvents from nuclear fuel reprocessing plant: Advances and perspectives","volume":"422","author":"Wang","year":"2024","journal-title":"Nucl. Eng. Des."},{"key":"ref_2","first-page":"1851","article-title":"Research Progress of Advanced Spent Nuclear Fuel Reprocessing Technology","volume":"59","author":"Zhang","year":"2025","journal-title":"At. Energy Sci. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"111383","DOI":"10.1016\/j.anucene.2025.111383","article-title":"Neutronic assessment of stable salt reactor with reprocessed fuels","volume":"218","author":"Silva","year":"2025","journal-title":"Ann. Nucl. Energy"},{"key":"ref_4","first-page":"301","article-title":"Determination of Total HDBP in Organic Solvent from Purex Process for Nuclear Fuel Reprocessing","volume":"59","author":"Xuan","year":"2025","journal-title":"At. Energy Sci. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"75787","DOI":"10.1109\/ACCESS.2025.3561920","article-title":"Digital Twins in Fusion Energy Research: Current State and Future Directions","volume":"13","author":"Battye","year":"2025","journal-title":"IEEE Access"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"113013","DOI":"10.1016\/j.nucengdes.2024.113013","article-title":"Digital twin challenges and opportunities for nuclear fuel manufacturing applications","volume":"420","author":"Bandala","year":"2024","journal-title":"Nucl. Eng. Des."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Sun, Q., Luo, Y., Zhang, W., Li, S., Li, J., Niu, K., Xiangrui, K., and Liu, W. (2025). Docs2KG: A Human-LLM Collaborative Approach to Unified Knowledge Graph Construction from Heterogeneous Documents. Companion Proceedings of the ACM on Web Conference 2025, ACM.","DOI":"10.1145\/3701716.3715309"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lipka, N., Rossi, R.A., Siu, A., Zhang, R., and Derr, T. (2024). Knowledge graph prompting for multi-document question answering. Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence, AAAI Press. AAAI\u201924\/IAAI\u201924\/EAAI\u201924.","DOI":"10.1609\/aaai.v38i17.29889"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Chen, S., Niu, L., Li, J., Zhu, X., Zhuang, X., and Ye, Y. (2025). Structured Element Extraction from Official Documents Based on BERT-CRF and Knowledge Graph-Enhanced Retrieval. Mathematics, 13.","DOI":"10.3390\/math13172779"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1007\/s12145-025-01870-5","article-title":"Fine-tuned BERT\u2013BiLSTM\u2013CRF approach for named entity recognition in geological disaster texts","volume":"18","author":"Li","year":"2025","journal-title":"Earth Sci. Inform."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"109743","DOI":"10.1016\/j.engappai.2024.109743","article-title":"A topic joint model for knowledge extraction from unstructured maintenance records","volume":"142","author":"Hu","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"173","DOI":"10.2967\/jnumed.124.268072","article-title":"Large Language Models and Large Multimodal Models in Medical Imaging: A Primer for Physicians","volume":"66","author":"Bradshaw","year":"2025","journal-title":"J. Nucl. Med."},{"key":"ref_13","first-page":"1","article-title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","volume":"43","author":"Huang","year":"2025","journal-title":"ACM Trans. Inf. Syst."},{"key":"ref_14","unstructured":"Tan, Z., and D\u2019Souza, J. (2026). Diagnosing Structural Failures in LLM-Based Evidence Extraction for Meta-Analysis. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1007\/s11390-025-5951-5","article-title":"General Framework of AI Agents","volume":"41","author":"Li","year":"2026","journal-title":"J. Comput. Sci. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Liu, A., Li, H., Wang, B., Yang, A., and Li, H. (July, January 30). RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution. Proceedings of the 2025 International Joint Conference on Neural Networks (IJCNN), Rome, Italy.","DOI":"10.1109\/IJCNN64981.2025.11228706"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"De Silva, E., and Asanka, D. (2025, January 16). Text to SQL AI Agentic Workflow Implementations: A Systematic Literature Review. Proceedings of the 2025 International Conference on Advances in Technology and Computing (ICATC), Kelaniya, Sri Lanka.","DOI":"10.1109\/ICATC68823.2025.11407744"},{"key":"ref_18","unstructured":"Ferrando, A., and Cardoso, R.C. (2025). Conversational Text-to-SQL: A Comprehensive Survey of Paradigms, Challenges, and Future Directions. Proceedings of the Agents and Robots for reliable Engineered Autonomy, Springer."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"7328","DOI":"10.1109\/TKDE.2025.3609486","article-title":"Next-Generation Database Interfaces: A Survey of LLM-Based Text-to-SQL","volume":"37","author":"Hong","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_20","first-page":"22124","article-title":"Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning","volume":"Volume 37","author":"Huang","year":"2024","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref_21","first-page":"3623","article-title":"Recent Advancement in Formation Control of Multi-Agent Systems: A Review","volume":"83","author":"Farooq","year":"2025","journal-title":"Comput. Mater. Contin."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"726","DOI":"10.26599\/BDMA.2024.9020098","article-title":"A Survey of Zero-Shot Object Detection","volume":"8","author":"Cao","year":"2025","journal-title":"Big Data Min. Anal."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3746224","article-title":"Few-Shot Learning for Medical Image Segmentation: A Review and Comparative Study","volume":"58","author":"Dissanayake","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"ref_24","first-page":"99","article-title":"Addressing Prompt Injection in Large Language Models via In-Context Learning","volume":"87","author":"Sato","year":"2026","journal-title":"Comput. Mater. Contin."},{"key":"ref_25","unstructured":"Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K.R., and Cao, Y. (2023, January 1\u20135). ReAct: Synergizing Reasoning and Acting in Language Models. Proceedings of the The Eleventh International Conference on Learning Representations, Kigali, Rwanda."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Li, B., Conen, J., and Aller, F. (2025, January 31). AID-Agent: An LLM-Agent for Advanced Extraction and Integration of Documents. Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025), Vienna, Austria.","DOI":"10.18653\/v1\/2025.realm-1.6"},{"key":"ref_27","first-page":"80","article-title":"Automated Data Mapping and Schema Matching For Improving Data Quality in Master Data Management","volume":"4","author":"Mishra","year":"2023","journal-title":"Int. J. Emerg. Trends Comput. Sci. Inf. Technol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1007\/s10462-025-11328-1","article-title":"Content moderation by LLM: From accuracy to legitimacy","volume":"58","author":"Huang","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Moayeri, M., Tabassi, E., and Feizi, S. (2024, January 3\u20136). WorldBench: Quantifying Geographic Disparities in LLM Factual Recall. Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency, FAccT \u201924, Rio de Janeiro, Brazil.","DOI":"10.1145\/3630106.3658967"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/5\/441\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T01:26:29Z","timestamp":1777857989000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/5\/441"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,3]]},"references-count":29,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["info17050441"],"URL":"https:\/\/doi.org\/10.3390\/info17050441","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,3]]}}}