{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T14:47:40Z","timestamp":1763131660810,"version":"3.45.0"},"reference-count":26,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Universidad de Ja\u00e9n through its Teaching Innovation Plan","award":["PID-UJA 2025\u20132029"],"award-info":[{"award-number":["PID-UJA 2025\u20132029"]}]},{"name":"Vicerrectorado de Formaci\u00f3n Permanente, Tecnolog\u00edas Educativas e Innovaci\u00f3n Docente","award":["PID2025_24 UJA"],"award-info":[{"award-number":["PID2025_24 UJA"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>This article formalizes AI-assisted assessment as a discrete-time policy-level design for iterative feedback and evaluates it in a digitally transformed higher-education setting. We integrate an agentic retrieval-augmented generation (RAG) feedback engine\u2014operationalized through planning (rubric-aligned task decomposition), tool use beyond retrieval (tests, static\/dynamic analyzers, rubric checker), and self-critique (checklist-based verification)\u2014into a six-iteration dynamic evaluation cycle. Learning trajectories are modeled with three complementary formulations: (i) an interpretable update rule with explicit parameters \u03b7 and \u03bb that links next-step gains to feedback quality and the gap-to-target and yields iteration-complexity and stability conditions; (ii) a logistic-convergence model capturing diminishing returns near ceiling; and (iii) a relative-gain regression quantifying the marginal effect of feedback quality on the fraction of the gap closed per iteration. In a Concurrent Programming course (n=35), the cohort mean increased from 58.4 to 91.2 (0\u2013100), while dispersion decreased from 9.7 to 5.8 across six iterations; a Greenhouse\u2013Geisser corrected repeated-measures ANOVA indicated significant within-student change. Parameter estimates show that higher-quality, evidence-grounded feedback is associated with larger next-step gains and faster convergence. Beyond performance, we engage the broader pedagogical question of what to value and how to assess in AI-rich settings: we elevate process and provenance\u2014planning artifacts, tool-usage traces, test outcomes, and evidence citations\u2014to first-class assessment signals, and outline defensible formats (trace-based walkthroughs and oral\/code defenses) that our controller can instrument. We position this as a design model for feedback policy, complementary to state-estimation approaches such as knowledge tracing. We discuss implications for instrumentation, equity-aware metrics, reproducibility, and epistemically aligned rubrics. Limitations include the observational, single-course design; future work should test causal variants (e.g., stepped-wedge trials) and cross-domain generalization.<\/jats:p>","DOI":"10.3390\/a18110712","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T08:57:41Z","timestamp":1762851461000},"page":"712","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Assessment with AI (Agentic RAG) and Iterative Feedback: A Model for the Digital Transformation of Higher Education in the Global EdTech Ecosystem"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2857-5693","authenticated-orcid":false,"given":"Rub\u00e9n","family":"Ju\u00e1rez","sequence":"first","affiliation":[{"name":"School of Engineering, Science, and Technology, UNIE Universidad, Calle Arapiles, 14, 28015 Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7807-4363","authenticated-orcid":false,"given":"Antonio","family":"Hern\u00e1ndez-Fern\u00e1ndez","sequence":"additional","affiliation":[{"name":"Department of Education, Faculty of Humanities and Educational Sciences, University of Ja\u00e9n, 23071 Ja\u00e9n, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2286-8674","authenticated-orcid":false,"given":"Claudia","family":"de Barros-Camargo","sequence":"additional","affiliation":[{"name":"Department MIDE I, Faculty of Education, National University of Distance Education (UNED), 28040 Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0392-4351","authenticated-orcid":false,"given":"David","family":"Molero","sequence":"additional","affiliation":[{"name":"Department of Education, Faculty of Humanities and Educational Sciences, University of Ja\u00e9n, 23071 Ja\u00e9n, Spain"},{"name":"Research Group \u201cLifelong Education, Neuropedagogical Integration (LE:NI)\u201d, University of Ja\u00e9n, 23071 Ja\u00e9n, Spain"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ogunleye, B., Zakariyyah, K.I., Ajao, O., Olayinka, O., and Sharma, H. (2024). A Systematic Review of Generative AI for Teaching and Learning Practice. Educ. Sci., 14.","DOI":"10.3390\/educsci14060636"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"124167","DOI":"10.1016\/j.eswa.2024.124167","article-title":"Artificial intelligence in education: A systematic literature review","volume":"252","author":"Wang","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Fleckenstein, J., Liebenow, L.W., and Meyer, J. (2023). Automated feedback and writing: A multi-level meta-analysis of effects on students\u2019 performance. Front. Artif. Intell., 6.","DOI":"10.3389\/frai.2023.1162454"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1377","DOI":"10.1080\/14703297.2024.2422337","article-title":"Generative AI in education: ChatGPT-4 in evaluating students\u2019 written responses","volume":"62","author":"Jauhiainen","year":"2025","journal-title":"Innov. Educ. Teach. Int."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"19649","DOI":"10.1007\/s10639-024-12633-y","article-title":"AI-experiments in education: An AI-driven randomized controlled trial for higher education research","volume":"29","author":"Cingillioglu","year":"2024","journal-title":"Educ. Inf. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Fan, W., Ding, Y., Ning, L., Wang, S., Li, H., Yin, D., Chua, T.-S., and Li, Q. (2024, January 25\u201329). A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented LLMs. Proceedings of the KDD \u201924: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Barcelona, Spain.","DOI":"10.1145\/3637528.3671470"},{"key":"ref_7","unstructured":"Gupta, S., Ranjan, R., and Singh, S.N. (2024). A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions. arXiv."},{"key":"ref_8","unstructured":"Asai, A., Wu, Z., Wang, Y., Sil, A., and Hajishirzi, H. (2023). Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection. arXiv."},{"key":"ref_9","unstructured":"Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y. (2023, January 1\u20135). ReAct: Synergizing Reasoning and Acting in Language Models. Proceedings of the International Conference on Learning Representations (ICLR 2023), Kigali, Rwanda."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3231711","article-title":"A Systematic Literature Review of Automated Feedback Generation for Programming Exercises","volume":"19","author":"Keuning","year":"2019","journal-title":"ACM Trans. Comput. Educ."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Jacobs, S., and Jaschke, S. (2024). Evaluating the Application of Large Language Models to Generate Feedback in Programming Education. arXiv.","DOI":"10.1109\/EDUCON60312.2024.10578838"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Nguyen, H., Stott, N., and Allan, V. (2024, January 18\u201320). Comparing Feedback from Large Language Models and Instructors: Teaching Computer Science at Scale. Proceedings of the Eleventh ACM Conference on Learning @ Scale (L@S \u201924), New York, NY, USA.","DOI":"10.1145\/3657604.3664660"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Koutcheme, C., and Hellas, A. (2024, January 18\u201320). Propagating Large Language Models Programming Feedback. Proceedings of the 11th ACM Conference on Learning at Scale (L@S \u201924), Atlanta, GA, USA.","DOI":"10.1145\/3657604.3664665"},{"key":"ref_14","unstructured":"Heickal, H., and Lan, A. (2024, January 14\u201317). Generating Feedback-Ladders for Logical Errors in Programming with LLMs. Proceedings of the 17th International Conference on Educational Data Mining (EDM 2024)\u2014Posters. International Educational Data Mining Society, Atlanta, GA, USA."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1186\/s41239-024-00455-4","article-title":"Feedback sources in essay writing: Peer-generated or AI-generated?","volume":"21","author":"Banihashem","year":"2024","journal-title":"Int. J. Educ. Technol. High. Educ."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3569576","article-title":"Knowledge Tracing: A Survey","volume":"55","author":"Abdelrahman","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"110036","DOI":"10.1016\/j.knosys.2022.110036","article-title":"A Survey on Deep Learning-Based Knowledge Tracing","volume":"258","author":"Song","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Yin, Y., Dai, L., Huang, Z., Shen, S., Wang, F., Liu, Q., Chen, E., and Li, X. (May, January 30). Tracing Knowledge Instead of Patterns: Stable Knowledge Tracing with Diagnostic Transformer. Proceedings of the ACM Web Conference 2023 (WWW \u201923). ACM, Austin, TX, USA.","DOI":"10.1145\/3543507.3583255"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Liu, T., Zhang, M., Zhu, C., and Chang, L. (2023). Transformer-based Convolutional Forgetting Knowledge Tracking. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-45936-0"},{"key":"ref_20","unstructured":"Zhou, T. (2023). Multi-Granularity Time-based Transformer for Student Performance Prediction. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"475","DOI":"10.3102\/0034654314564881","article-title":"Effects of Feedback in a Computer-Based Learning Environment on Students\u2019 Learning Outcomes: A Meta-Analysis","volume":"85","author":"Feskens","year":"2015","journal-title":"Rev. Educ. Res."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Palla, K., Garc\u00eda, J.L.R., Hauff, C., Fabbri, F., Damianou, A., Lindstr, M.H., Taber, D., and Lalmas, M. (2025, January 23\u201326). Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models. Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, Athens, Greece.","DOI":"10.1145\/3715275.3732054"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Heo, J., Jeong, H., Choi, D., and Lee, E. (2023, January 14\u201320). REFERENT: Transformer-based Feedback Generation using Assignment Information for Programming Course. Proceedings of the 2023 IEEE\/ACM 45th International Conference on Software Engineering: Software Engineering Education and Training (ICSE-SEET), Melbourne, Australia.","DOI":"10.1109\/ICSE-SEET58685.2023.00035"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"56720","DOI":"10.1109\/ACCESS.2022.3177752","article-title":"A review of the trends and challenges in adopting natural language processing methods for education feedback analysis","volume":"10","author":"Shaik","year":"2022","journal-title":"IEEE Access"},{"key":"ref_25","first-page":"100234","article-title":"Assessing the Proficiency of Large Language Models in Automatic Feedback Generation: An Evaluation Study","volume":"5","author":"Dai","year":"2024","journal-title":"Comput. Educ. Artif. Intell."},{"key":"ref_26","unstructured":"Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., K\u00fcttler, H., Lewis, M., Yih, W.t., and Rockt\u00e4schel, T. (2020, January 6\u201312). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Proceedings of the Advances in Neural Information Processing Systems 33 (NeurIPS 2020), Virtual."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/11\/712\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T14:44:41Z","timestamp":1763131481000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/11\/712"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"references-count":26,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["a18110712"],"URL":"https:\/\/doi.org\/10.3390\/a18110712","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2025,11,11]]}}}