Elamur Research⌕
☰
home / papers / 2026 / LearnerCoMPASS: Intelligent Tutoring System with Dynamic Cognitive Diagnosis and Multi-Model Path Planning

LearnerCoMPASS: Intelligent Tutoring System with Dynamic Cognitive Diagnosis and Multi-Model Path Planning

Paper · 2026 · Ziji Sheng, Guiyao Tie, Weidong Wang et al.

Summary

LearnerCoMPASS addresses adaptive learning path recommendation in STEM subjects. In this setting, LLM-based tutors have three weaknesses: they track a learner's changing knowledge too slowly, they invent facts, and they plan curricula with little foresight. The authors propose a closed-loop, end-to-end tutoring framework with three components:

  • Hybrid Knowledge Graph. A static prerequisite graph, built from curated data such as Junyi, is combined with small subgraphs assembled on demand from web search. Candidate triples are filtered for schema, permitted relation types and cycles. They are then embedded, stored in Neo4j and supplied to the LLM through Graph-RAG.
  • Cognitive diagnosis. A multi-agent encoder-decoder estimates the learner's proficiency vector during inference without any retraining. The encoder produces a coarse initial estimate, and the decoder refines it iteratively.
  • Path planning. An adapted Adaptive Branching MCTS (AB-MCTS-M) with Bayesian reward estimation coordinates several heterogeneous LLMs to search for good learning sequences.

The system outperforms neural cognitive diagnosis baselines and sharply reduces hallucinations. This makes it a step toward reliable AI tutoring in high-stakes STEM education.

Key points

  • On the Eedi dataset, cognitive diagnosis reaches an ACC of 0.678, which is 3.8% above the strongest baseline, NeuralCDM. On a private Linear Algebra dataset, accuracy is 0.822 versus 0.745 for NeuralCDM.
  • Hallucinations were measured with a RAGTruth-style protocol: experts checked atomic claims in 1,000 generated outputs against the knowledge graph.
  • The hallucination rate falls from 31.5% for the base LLM to 10.6% with Graph-RAG, and to 4.1% with the full verification loop.
  • "Evident Conflicts" drop from 32 to 2 in diagnosis and from 8 to 0 in planning. "Subtle Baseless Info" drops from 55 to 15.
  • The authors list three limitations: high inference latency, dependence on the quality of the knowledge graph, and evaluation done mostly in simulated settings or on static data rather than in real classrooms.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Huazhong University of Science and TechnologyWuhan · China45 works · 6,345 citations🎓Wuhan UniversityWuhan · China35 works · 1,127 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksInformation Systems · 1,437 worksComputer Science Applications · 102 works

Cite

Cite as Ziji Sheng, Guiyao Tie, Weidong Wang, Pan Zhou and Daizong Liu. 2026. LearnerCoMPASS: Intelligent Tutoring System with Dynamic Cognitive Diagnosis and Multi-Model Path Planning. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.408

@inproceedings{sheng2026learnercompass,
  title = {{LearnerCoMPASS: Intelligent Tutoring System with Dynamic Cognitive Diagnosis and Multi-Model Path Planning}},
  author = {Ziji Sheng, Guiyao Tie, Weidong Wang, Pan Zhou and Daizong Liu},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.408},
  url = {https://doi.org/10.18653/v1/2026.acl-long.408}
}

References

82 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Anton Andreychuk, Konstantin Yakovlev, Aleksandr Panov, and Alexey Skrynnik. 2025. Mapf-gpt: Imitation learning for multi-agent pathfinding at scale. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 23126–23134. find
  2. Yoav Bergner, Peter Halpin, and Jill-Jênn Vie. 2022. Multidimensional item response theory in the style of collaborative filtering. Psychometrika, 87(1):266–288. find
  3. Jonathan M Breiner, Shelly Sheats Harkness, Carla C Johnson, and Catherine M Koehler. 2012. What is stem? a discussion about conceptions of stem in education and partnerships. School science and mathematics, 112(1):3–11. find
  4. Chenyang Bu, Zhiyong Cao, Chenlong He, and Yuhong Zhang. 2023. Probabilistic model with evolutionary optimization for cognitive diagnosis. In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO ’23, page 891–899, New York, NY, USA. Association for Computing Machinery. find
  5. Xiaowen Cai, Daizong Liu, Xiaoye Qu, Xiang Fang, Jianfeng Dong, Keke Tang, Pan Zhou, Lichao Sun, and Wei Hu. 2025. Towards building model/prompt-transferable attackers against large vision-language models. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. find
  6. Haw-Shiuan Chang, Hwai-Jung Hsu, Kuan-Ta Chen, et al. 2015. Modeling exercise relationships in e-learning: A unified approach. In EDM, pages 532– 535. find
  7. Jinsong Chen and Jimmy de la Torre. 2013. A general cognitive diagnosis model for expert-defined polytomous attributes. Applied Psychological Measurement, 37(6):419–437. find
  8. Xin Chen, Jin Zhang, Tong Zhou, and Feng Zhang. 2025. Llm-cdm: A large language model enhanced cognitive diagnosis for intelligent education. Ieee Access. find
  9. Yanan Chen, Ali Pesaranghader, Tanmana Sadhu, and Dong Hoon Yi. 2024. Can we rely on llm agents to draft long-horizon plans? let’s take travelplanner as an example. arXiv preprint arXiv:2408.06318. — [arXiv:2408.06318](https://arxiv.org/abs/2408.06318) find
  10. Xinghe Cheng, Zihan Zhang, Jiapu Wang, Liangda Fang, Chaobo He, Quanlong Guan, Shirui Pan, and Weiqi Luo. 2025. GraphRAG-induced dual knowledge structure graphs for personalized learning path recommendation. Preprint, arXiv:2506.22303. — [arXiv:2506.22303](https://arxiv.org/abs/2506.22303) find
  11. Jimmy de la Torre. 2009. Dina model and parameter estimation: A didactic. Journal of Educational and Behavioral Statistics, 34(1):115–130. find
  12. Zhiang Dong, Jingyuan Chen, and Fei Wu. 2025a. Knowledge is power: Harnessing large language models for enhanced cognitive diagnosis. Proceedings of the AAAI Conference on Artificial Intelligence, 39(1):164–172. find
  13. Zhiang Dong, Jingyuan Chen, and Fei Wu. 2025b. Llm-driven cognitive diagnosis with solo taxonomy: A model-agnostic framework. Frontiers of Digital Education, 2(2):20. find
  14. Xiang Fang, Wanlong Fang, Daizong Liu, Xiaoye Qu, Jianfeng Dong, Pan Zhou, Renfu Li, Zichuan Xu, Lixing Chen, Panpan Zheng, et al. 2024a. Not all inputs are valid: Towards open-set video moment retrieval using language. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 28–… find
  15. Xiang Fang, Daizong Liu, Pan Zhou, and Guoshun Nan. 2023b. You can ground earlier than see: An effective and efficient pipeline for temporal sentence grounding in compressed videos. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2448–2460. find
  16. Xiang Fang, Daizong Liu, Pan Zhou, Zichuan Xu, and Ruixuan Li. 2023c. Hierarchical local-global transformer for temporal sentence grounding. IEEE Transactions on Multimedia, 26:3263–3277. find
  17. Xiang Fang, Zeyu Xiong, Wanlong Fang, Xiaoye Qu, Chen Chen, Jianfeng Dong, Keke Tang, Pan Zhou, Yu Cheng, and Daizong Liu. 2024b. Rethinking weakly-supervised video temporal grounding from a game perspective. In European Conference on Computer Vision, pages 290–311. Springer. find
  18. Zhaohan Feng, Ruiqi Xue, Lei Yuan, Yang Yu, Ning Ding, Meiqin Liu, Bingzhao Gao, Jian Sun, Xinhu Zheng, and Gang Wang. 2025. Multi-agent embodied ai: Advances and future directions. arXiv preprint arXiv:2505.05108. — [arXiv:2505.05108](https://arxiv.org/abs/2505.05108) find
  19. Reva Freedman, Yujian Zhou, Michael Glass, Jung Hee Kim, and Martha W Evens. 2022. Using rule induction to assist in rule construction for a natural-language based intelligent tutoring system. In Proceedings of the Twentieth Annual Conference of the Cognitive Science Society, pages 362–367. Routledg… find
  20. Weibo Gao, Qi Liu, Zhenya Huang, Yu Yin, Haoyang Bi, Mu-Chun Wang, Jianhui Ma, Shijin Wang, and Yu Su. 2021. RCD: Relation map driven cognitive diagnosis for intelligent education systems. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrie… find
  21. Ilie Gligorea, Marius Cioca, Romana Oancea, Andra-Teodora Gorski, Hortensia Gorski, and Paul Tudorache. 2023. Adaptive learning using artificial intelligence in e-learning: A literature review. Education Sciences, 13(12):1216. find
  22. Xiang Fang, Wanlong Fang, Changshuo Wang, Daizong Liu, Keke Tang, Jianfeng Dong, Pan Zhou, and Beibei Li. 2025. Multi-pair temporal sentence grounding via multi-thread knowledge transfer network. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 2915–2923. find
  23. Haoyu Han, Yu Wang, Harry Shomer, Kai Guo, Jiayuan Ding, Yongjia Lei, Mahantesh Halappanavar, Ryan A. Rossi, Subhabrata Mukherjee, Xianfeng Tang, Qi He, Zhigang Hua, Bo Long, Tong Zhao, Neil Shah, Amin Javari, Yinglong Xia, and Jiliang Tang. 2025a. Retrieval-augmented generation with graphs (graphra… find
  24. Xiang Fang, Daizong Liu, Wanlong Fang, Pan Zhou, Yu Cheng, Keke Tang, and Kai Zou. 2023a. Annotations are not all you need: A cross-modal knowledge transfer network for unsupervised temporal sentence grounding. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8721– 873… find
  25. Ze Han, Yu Su, Qi Mo, and Xinyu Nie. 2025b. Neural network student cognitive diagnosis model based on multi-relational graph. In Proceedings of the 2025 2nd International Conference on Generative Artificial Intelligence and Information Security, GAIIS 2025, pages 515–521, Hangzhou, China. ACM. find
  26. Xiang Fang, Daizong Liu, Pan Zhou, and Yuchong Hu. 2022. Multi-modal cross-domain alignment network for video moment retrieval. IEEE Transactions on Multimedia, 25:7517–7532. find
  27. Huu-Tuong Ho, Duc-Tin Ly, and Luong Vuong Nguyen. 2024. Mitigating hallucinations in large language models for educational application. In 2024 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), pages 1–4. IEEE. find
  28. Yuichi Inoue, Kou Misaki, Yuki Imajuku, So Kuroki, Taishi Nakamura, and Takuya Akiba. 2025. Wider or deeper? scaling LLM inference-time compute with adaptive branching tree search. Preprint, arXiv:2503.04412. — [arXiv:2503.04412](https://arxiv.org/abs/2503.04412) find
  29. Daizong Liu, Xiang Fang, Pan Zhou, Xing Di, Weining Lu, and Yu Cheng. 2023a. Hypotheses tree building for one-shot temporal sentence localization. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 1640–1648. find
  30. L. M. R. Jayasinghe and Dharshana Kasthurirathna. 2022. A goal-driven personalized educational content recommendation system for self-learning. International Journal of Advanced Computer Science and Applications, 13(11). find
  31. Daizong Liu, Wangqin Liu, Xiaowen Cai, Pan Zhou, Runwei Guan, Xiaoye Qu, and Bo Du. 2026c. Generating transferable attacks across large vision-language models using adversarial deformation learning. Pattern Recognition, page 113194. find
  32. Weiqiang Jin, Hongyang Du, Biao Zhao, Xingwu Tian, Bohang Shi, and Guang Yang. 2025. A comprehensive survey on multi-agent cooperative decision-making: Scenarios, approaches, challenges and perspectives. arXiv preprint arXiv:2503.13415. — [arXiv:2503.13415](https://arxiv.org/abs/2503.13415) find
  33. Daizong Liu, Xiaoye Qu, Xing Di, Yu Cheng, Zichuan Xu, and Pan Zhou. 2022a. Memory-guided semantic learning network for temporal sentence grounding. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 1665–1673. find
  34. Jeff Johns, Sridhar Mahadevan, and Beverly Woolf. 2006. Estimating student proficiency using an item response theory model. In International conference on intelligent tutoring systems, pages 473–480. Springer. find
  35. Daizong Liu, Xiaoye Qu, Jianfeng Dong, and Pan Zhou. 2021a. Adaptive proposal generation network for temporal sentence localization in videos. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9292–9301. find
  36. Ankur Joshi, Saket Kale, Satish Chandel, and D Kumar Pal. 2015. Likert scale: Explored and explained. British journal of applied science & technology, 7(4):396. find
  37. Daizong Liu, Xiaoye Qu, Jianfeng Dong, Pan Zhou, Yu Cheng, Wei Wei, Zichuan Xu, and Yulai Xie. 2021b. Context-aware biaffine localizing network for temporal sentence grounding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11235–11244. find
  38. Jonathan Larson and Steven Truitt. 2024. Graphrag: Unlocking llm discovery on narrative private data. Microsoft Research Blog. find
  39. Guangquan Li, Yuqing Hu, Junkai Shuai, Tonghua Yang, Yonghong Zhang, Shiming Dai, and Naixue Xiong. 2022. Neuralncd: A neural network cognitive diagnosis model based on multi-dimensional features. Applied Sciences, 12(19). find
  40. Wenyi Liao. 2025. Study on learning path optimization based on reinforcement learning and collaborative filtering. In Second International Conference on Big Data, Computational Intelligence, and Applications (BDCIA 2024), volume 13550, pages 878–885. SPIE. find
  41. Joy Jia Yin Lim, Ye He, Jifan Yu, Xin Cong, Daniel Zhang-Li, Zhiyuan Liu, Huiqin Liu, Lei Hou, Juanzi Li, and Bin Xu. 2025. Personalized learning path planning with goal-driven learner state modeling. Preprint, arXiv:2510.13215. — [arXiv:2510.13215](https://arxiv.org/abs/2510.13215) find
  42. Chunmao Liu, Somkiat Tuntiwongwanich, and Thiya-porn Kantathanawat. 2025. Artificial intelligence-driven cognitive diagnosis and adaptive learning: The impact of online course stickiness and learning skills. find
  43. Daizong Liu, Xiaowen Cai, Pan Zhou, Xiaoye Qu, Lichao Sun, and Wei Hu. 2026a. Are large vision-language models robust to adversarial visual transformations? IEEE Transactions on Information Forensics and Security. find
  44. Daizong Liu, Baoquan Chen, and Wei Hu. 2026b. Spatial-spectral homogeneous attacks on physical-world large vision-language models. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 7114–7122. find
  45. Daizong Liu, Xiaoye Qu, and Wei Hu. 2022b. Reducing the vision and language bias for temporal sentence grounding. In Proceedings of the 30th ACM International Conference on Multimedia, pages 4092–4101. find
  46. Daizong Liu, Xiaoye Qu, Xiao-Yang Liu, Jianfeng Dong, Pan Zhou, and Zichuan Xu. 2020. Jointly cross-and self-modal graph attention network for query-based moment localization. In Proceedings of the 28th ACM International Conference on Multimedia, pages 4070–4078. find
  47. Daizong Liu, Xiaoye Qu, Yinzhen Wang, Xing Di, Kai Zou, Yu Cheng, Zichuan Xu, and Pan Zhou. 2022c. Unsupervised temporal video grounding with deep semantic clustering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 1683–1691. find
  48. Daizong Liu, Shuangjie Xu, Xiao-Yang Liu, Zichuan Xu, Wei Wei, and Pan Zhou. 2021c. Spatiotemporal graph neural network based mask reconstruction for video object segmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 2100–2108. find
  49. Daizong Liu, Mingyu Yang, Xiaoye Qu, Pan Zhou, Yu Cheng, and Wei Hu. 2024a. A survey of attacks on large vision-language models: Resources, advances, and future trends. arXiv preprint arXiv:2407.07403. — [arXiv:2407.07403](https://arxiv.org/abs/2407.07403) find
  50. Daizong Liu, Mingyu Yang, Xiaoye Qu, Pan Zhou, Xiang Fang, Keke Tang, Yao Wan, and Lichao Sun. 2024b. Pandora’s box: Towards building universal attackers against real-world large vision-language models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. find
  51. Yingjie Liu, Tiancheng Zhang, Xuecen Wang, Ge Yu, and Tao Li. 2023b. New development of cognitive diagnosis models. Frontiers of Computer Science, 17(1):171604. find
  52. Lin Lu, Zhigang Zuo, Ziji Sheng, and Pan Zhou. 2025. Merger-as-a-stealer: Stealing targeted pii from aligned llms with model merging. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 5817–5836. find
  53. Rui Lv, Qi Liu, Weibo Gao, Haotian Zhang, Junyu Lu, and Linbo Zhu. 2025. Genal: Generative agent for adaptive learning. Proceedings of the AAAI Conference on Artificial Intelligence, 39(1):577–585. find
  54. Haiping Ma, Manwei Li, Le Wu, Haifeng Zhang, Yunbo Cao, Xingyi Zhang, and Xuemin Zhao. 2022. Knowledge-sensed cognitive diagnosis for intelligent education platforms. In Proceedings of the 31st ACM international conference on information & knowledge management, pages 1451–1460. meta llama. 2025. Lla… find
  55. Olga Tapalova and Nadezhda Zhiyenbayeva. 2022. Artificial intelligence in education: Aied for personalised learning pathways. Electronic Journal of e-Learning, 20(5):639–653. find
  56. Guiyao Tie, Tianyao Luo, Xueyang Zhou, Chaoran Hu, Yunhong He, Junran Wu, Yuanfan Yao, Pan Zhou, and Lichao Sun. Routejudge: Benchmarking llm-asa-judge with routing strategies. find
  57. Guiyao Tie, Zenghui Yuan, Zeli Zhao, Chaoran Hu, Tianhe Gu, Ruihang Zhang, Sizhe Zhang, Junran Wu, Xiaoyue Tu, Ming Jin, et al. 2025a. Can llms correct themselves? a benchmark of self-correction in llms. arXiv preprint arXiv:2510.16062. — [arXiv:2510.16062](https://arxiv.org/abs/2510.16062) find
  58. Guiyao Tie, Zeli Zhao, Dingjie Song, Fuyang Wei, Rong Zhou, Yurou Dai, Wen Yin, Zhejian Yang, Jiangyue Yan, Yao Su, et al. 2025b. A survey on post-training of large language models. arXiv preprint arXiv:2503.06072. — [arXiv:2503.06072](https://arxiv.org/abs/2503.06072) find
  59. Dong-Bo Tu, Yan Cai, Hai-Qi Dai, and Shu-Liang Ding. 2011. A polytomous cognitive diagnosis model: P-dina model. Acta Psychologica Sinica, 42:1011– 1020. find
  60. OpenAI. 2025. GPT-5.2. https://www.openai.com. Large language model. ↗
  61. Fei Wang, Qi Liu, Enhong Chen, Zhenya Huang, Yuying Chen, Yu Yin, Zai Huang, and Shijin Wang. 2020. Neural cognitive diagnosis for intelligent education systems. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04):6153–6161. find
  62. OpenAI, Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276.
  63. Fei Wang, Qi Liu, Enhong Chen, Zhenya Huang, Yu Yin, Shijin Wang, and Yu Su. 2022. Neuralcd: a general framework for cognitive diagnosis. IEEE Transactions on Knowledge and Data Engineering, 35(8):8312–8327. find
  64. Qwen. 2025. Qwen3-235b-a22b-instruct-2507. Accessed: 2025-08-10. find
  65. Tianfu Wang, Yi Zhan, Jianxun Lian, Zhengyu Hu, Nicholas Jing Yuan, Qi Zhang, Xing Xie, and Hui Xiong. 2025a. LLM-powered multi-agent framework for goal-oriented learning in intelligent tutoring system. In Companion Proceedings of the ACM on Web Conference 2025, WWW ’25 Companion, pages 510– 519, Sy… find
  66. Jiawen Shi, Zenghui Yuan, Yinuo Liu, Yue Huang, Pan Zhou, Lichao Sun, and Neil Zhenqiang Gong. 2024. Optimization-based prompt injection attack to llm-asa-judge. In Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security, pages 660–674. find
  67. Zhaoyu Shou, Xianying Lu, Zhengzheng Wu, Hua Yuan, Huibing Zhang, and Junli Lai. 2020. On learning path planning algorithm based on collaborative analysis of learning behavior. IEEE Access, 8:119863– 119879. find
  68. Tianfu Wang, Yi Zhan, Jianxun Lian, Zhengyu Hu, Nicholas Jing Yuan, Qi Zhang, Xing Xie, and Hui Xiong. 2025b. Llm-powered multi-agent framework for goal-oriented learning in intelligent tutoring system. In Companion Proceedings of the ACM on Web Conference 2025, pages 510–519. find
  69. Marlene Steinbach, Shreya Bhandari, Jennifer Meyer, and Zachary A Pardos. 2025. When llms hallucinate: Examining the effects of erroneous feedback in math tutoring systems. In Proceedings of the Twelfth ACM Conference on Learning@ Scale, pages 139–150. find
  70. Zichao Wang, Angus Lamb, Evgeny Saveliev, Pashmina Cameron, Jordan Zaykov, Jose Miguel Hernandez-Lobato, Richard E Turner, Richard G Baraniuk, Craig Barton, Simon Peyton Jones, et al. 2021. Results and insights from diagnostic questions: The neurips 2020 education challenge. In NeurIPS 2020 Competit… find
  71. Weiwei Sun, Miao Lu, Zhan Ling, Kang Liu, Xuesong Yao, Yiming Yang, and Jiecao Chen. 2025. Scaling long-horizon llm agent via context-folding. arXiv preprint arXiv:2510.11967. — [arXiv:2510.11967](https://arxiv.org/abs/2510.11967) find
  72. Qingsong Wen, Jing Liang, Carles Sierra, Rose Luckin, Richard Tong, Zitao Liu, Peng Cui, and Jiliang Tang. 2024. Ai for education (ai4edu): Advancing personalized education with llm and adaptive learning. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages… find
  73. Yuanhao Wu, Juno Zhu, Siliang Xu, Kashun Shum, Cheng Niu, Randy Zhong, Juntong Song, and Tong Zhang. 2023. Ragtruth: A hallucination corpus for developing trustworthy retrieval-augmented language models. Preprint, arXiv:2401.00396.
  74. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yi Ding, Boyang Hong, Ming Zhang, et al. 2023. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864.
  75. Zhishang Xiang, Chuanjie Wu, Qinggang Zhang, Shengyuan Chen, Zijin Hong, Xiao Huang, and Jinsong Su. 2025. When to use graphs in rag: A comprehensive analysis for graph retrieval-augmented generation. arXiv preprint arXiv:2506.05690. — [arXiv:2506.05690](https://arxiv.org/abs/2506.05690) find
  76. Yu Xie, Michael Fang, and Kimberlee Shauman. 2015. Stem education. Annual review of sociology, 41(1):331–357. find
  77. Hai Yan, Haijian Ma, Xiaowen Cai, Daizong Liu, Zenghui Yuan, Xiaoye Qu, Jianfeng Dong, Runwei Guan, Xiang Fang, Hongyang He, et al. 2025. Fit the distribution: Cross-image/prompt adversarial attacks on multimodal large language models. In The Thirty-ninth Annual Conference on Neural Information Proc… find
  78. Chun-Kit Yeung. 2019. Deep-irt: Make deep learning based knowledge tracing explainable using item response theory. Preprint, arXiv:1904.11738. — [arXiv:1904.11738](https://arxiv.org/abs/1904.11738) find
  79. Peida Zhan, Wen-Chung Wang, Hong Jiao, and Yufang Bian. 2018. Probabilistic-input, noisy conjunctive models for cognitive diagnosis. Frontiers in Psychology, Volume 9 - 2018. find
  80. Xueqiao Zhang, Chao Zhang, Jianwen Sun, Jun Xiao, Yi Yang, and Yawei Luo. 2025a. Eduplanner: Llm-based multiagent systems for customized and intelligent instructional design. IEEE Transactions on Learning Technologies, 18:416–427. find
  81. Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, et al. 2025b. Qwen3 embedding: Advancing text embedding and reranking through foundation models. arXiv preprint arXiv:2506.05176.
  82. Andy Zhou, Kai Yan, Michal Shlapentokh-Rothman, Haohan Wang, and Yu-Xiong Wang. 2023. Language agent tree search unifies reasoning acting and planning in language models. arXiv preprint arXiv:2310.04406. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/sheng-2026-learnercompass-intelligent-tutoring-system-dynamic/