% Bibliografia do AI for Educational Assistants
%
% Regra do projeto: toda entrada precisa ser real e verificada no Google Scholar,
% no arXiv ou pelo DOI. Nunca inclua referência inventada.
%
% Esta é uma bibliografia inicial com trabalhos canônicos da área, que serve de
% base para os módulos. Novas entradas devem ser verificadas antes de entrar.

@inproceedings{vaswani2017attention,
  title     = {Attention Is All You Need},
  author    = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N. and Kaiser, Lukasz and Polosukhin, Illia},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2017},
  note      = {arXiv:1706.03762}
}

@article{mikolov2013efficient,
  title   = {Efficient Estimation of Word Representations in Vector Space},
  author  = {Mikolov, Tomas and Chen, Kai and Corrado, Greg and Dean, Jeffrey},
  journal = {arXiv preprint arXiv:1301.3781},
  year    = {2013}
}

@inproceedings{mikolov2013distributed,
  title     = {Distributed Representations of Words and Phrases and their Compositionality},
  author    = {Mikolov, Tomas and Sutskever, Ilya and Chen, Kai and Corrado, Greg and Dean, Jeffrey},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2013},
  note      = {arXiv:1310.4546}
}

@inproceedings{pennington2014glove,
  title     = {GloVe: Global Vectors for Word Representation},
  author    = {Pennington, Jeffrey and Socher, Richard and Manning, Christopher D.},
  booktitle = {Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  pages     = {1532--1543},
  year      = {2014},
  doi       = {10.3115/v1/D14-1162}
}

@article{bojanowski2017enriching,
  title   = {Enriching Word Vectors with Subword Information},
  author  = {Bojanowski, Piotr and Grave, Edouard and Joulin, Armand and Mikolov, Tomas},
  journal = {Transactions of the Association for Computational Linguistics (TACL)},
  volume  = {5},
  pages   = {135--146},
  year    = {2017},
  note    = {arXiv:1607.04606}
}

@article{hochreiter1997lstm,
  title   = {Long Short-Term Memory},
  author  = {Hochreiter, Sepp and Schmidhuber, J{\"u}rgen},
  journal = {Neural Computation},
  volume  = {9},
  number  = {8},
  pages   = {1735--1780},
  year    = {1997},
  doi     = {10.1162/neco.1997.9.8.1735}
}

@inproceedings{cho2014gru,
  title     = {Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation},
  author    = {Cho, Kyunghyun and van Merri{\"e}nboer, Bart and Gulcehre, Caglar and Bahdanau, Dzmitry and Bougares, Fethi and Schwenk, Holger and Bengio, Yoshua},
  booktitle = {Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year      = {2014},
  note      = {arXiv:1406.1078}
}

@inproceedings{devlin2019bert,
  title     = {BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding},
  author    = {Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
  booktitle = {Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)},
  year      = {2019},
  note      = {arXiv:1810.04805}
}

@inproceedings{brown2020gpt3,
  title     = {Language Models are Few-Shot Learners},
  author    = {Brown, Tom B. and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and others},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2020},
  note      = {arXiv:2005.14165}
}

@inproceedings{reimers2019sbert,
  title     = {Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks},
  author    = {Reimers, Nils and Gurevych, Iryna},
  booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year      = {2019},
  note      = {arXiv:1908.10084}
}

@inproceedings{lewis2020rag,
  title     = {Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks},
  author    = {Lewis, Patrick and Perez, Ethan and Piktus, Aleksandra and Petroni, Fabio and Karpukhin, Vladimir and Goyal, Naman and K{\"u}ttler, Heinrich and Lewis, Mike and Yih, Wen-tau and Rockt{\"a}schel, Tim and Riedel, Sebastian and Kiela, Douwe},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2020},
  note      = {arXiv:2005.11401}
}

@inproceedings{wei2022cot,
  title     = {Chain-of-Thought Prompting Elicits Reasoning in Large Language Models},
  author    = {Wei, Jason and Wang, Xuezhi and Schuurmans, Dale and Bosma, Maarten and Ichter, Brian and Xia, Fei and Chi, Ed H. and Le, Quoc V. and Zhou, Denny},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2022},
  note      = {arXiv:2201.11903}
}

@inproceedings{ouyang2022instructgpt,
  title     = {Training Language Models to Follow Instructions with Human Feedback},
  author    = {Ouyang, Long and Wu, Jeffrey and Jiang, Xu and Almeida, Diogo and Wainwright, Carroll L. and Mishkin, Pamela and Zhang, Chong and Agarwal, Sandhini and Slama, Katarina and Ray, Alex and others},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2022},
  note      = {arXiv:2203.02155}
}

@inproceedings{yao2023react,
  title     = {ReAct: Synergizing Reasoning and Acting in Language Models},
  author    = {Yao, Shunyu and Zhao, Jeffrey and Yu, Dian and Du, Nan and Shafran, Izhak and Narasimhan, Karthik and Cao, Yuan},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year      = {2023},
  note      = {arXiv:2210.03629}
}

@article{turing1950computing,
  title   = {Computing Machinery and Intelligence},
  author  = {Turing, Alan M.},
  journal = {Mind},
  volume  = {59},
  number  = {236},
  pages   = {433--460},
  year    = {1950},
  doi     = {10.1093/mind/LIX.236.433}
}

@article{mccarthy1955dartmouth,
  title   = {A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence},
  author  = {McCarthy, John and Minsky, Marvin L. and Rochester, Nathaniel and Shannon, Claude E.},
  journal = {AI Magazine},
  volume  = {27},
  number  = {4},
  pages   = {12--14},
  year    = {2006},
  note    = {Proposta original de 1955, reimpressa em 2006},
  doi     = {10.1609/aimag.v27i4.1904}
}

@book{russell2020aima,
  title     = {Artificial Intelligence: A Modern Approach},
  author    = {Russell, Stuart and Norvig, Peter},
  edition   = {4},
  publisher = {Pearson},
  year      = {2020}
}

@book{goodfellow2016deep,
  title     = {Deep Learning},
  author    = {Goodfellow, Ian and Bengio, Yoshua and Courville, Aaron},
  publisher = {MIT Press},
  year      = {2016},
  note      = {Dispon{\'i}vel em https://www.deeplearningbook.org}
}

@book{mitchell1997machine,
  title     = {Machine Learning},
  author    = {Mitchell, Tom M.},
  publisher = {McGraw-Hill},
  year      = {1997}
}

@inproceedings{goodfellow2014gan,
  title     = {Generative Adversarial Nets},
  author    = {Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2014},
  note      = {arXiv:1406.2661}
}

@article{rosenblatt1958perceptron,
  title   = {The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain},
  author  = {Rosenblatt, Frank},
  journal = {Psychological Review},
  volume  = {65},
  number  = {6},
  pages   = {386--408},
  year    = {1958},
  doi     = {10.1037/h0042519}
}

@book{minsky1969perceptrons,
  title     = {Perceptrons: An Introduction to Computational Geometry},
  author    = {Minsky, Marvin and Papert, Seymour},
  publisher = {MIT Press},
  year      = {1969}
}

@article{rumelhart1986backprop,
  title   = {Learning Representations by Back-Propagating Errors},
  author  = {Rumelhart, David E. and Hinton, Geoffrey E. and Williams, Ronald J.},
  journal = {Nature},
  volume  = {323},
  number  = {6088},
  pages   = {533--536},
  year    = {1986},
  doi     = {10.1038/323533a0}
}

@inproceedings{krizhevsky2012imagenet,
  title     = {ImageNet Classification with Deep Convolutional Neural Networks},
  author    = {Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E.},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2012}
}

@article{newell1976symbols,
  title   = {Computer Science as Empirical Inquiry: Symbols and Search},
  author  = {Newell, Allen and Simon, Herbert A.},
  journal = {Communications of the ACM},
  volume  = {19},
  number  = {3},
  pages   = {113--126},
  year    = {1976},
  doi     = {10.1145/360018.360022}
}

@article{mccarthy1960lisp,
  title   = {Recursive Functions of Symbolic Expressions and Their Computation by Machine, Part I},
  author  = {McCarthy, John},
  journal = {Communications of the ACM},
  volume  = {3},
  number  = {4},
  pages   = {184--195},
  year    = {1960},
  doi     = {10.1145/367177.367199}
}

@book{buchanan1984mycin,
  title     = {Rule-Based Expert Systems: The MYCIN Experiments of the Stanford Heuristic Programming Project},
  author    = {Buchanan, Bruce G. and Shortliffe, Edward H.},
  publisher = {Addison-Wesley},
  year      = {1984}
}

@article{samuel1959checkers,
  title   = {Some Studies in Machine Learning Using the Game of Checkers},
  author  = {Samuel, Arthur L.},
  journal = {IBM Journal of Research and Development},
  volume  = {3},
  number  = {3},
  pages   = {210--229},
  year    = {1959},
  doi     = {10.1147/rd.33.0210}
}

@book{bishop2006prml,
  title     = {Pattern Recognition and Machine Learning},
  author    = {Bishop, Christopher M.},
  publisher = {Springer},
  year      = {2006}
}

@book{hastie2009esl,
  title     = {The Elements of Statistical Learning: Data Mining, Inference, and Prediction},
  author    = {Hastie, Trevor and Tibshirani, Robert and Friedman, Jerome},
  edition   = {2},
  publisher = {Springer},
  year      = {2009}
}

@article{domingos2012useful,
  title   = {A Few Useful Things to Know about Machine Learning},
  author  = {Domingos, Pedro},
  journal = {Communications of the ACM},
  volume  = {55},
  number  = {10},
  pages   = {78--87},
  year    = {2012},
  doi     = {10.1145/2347736.2347755}
}

@article{shannon1948communication,
  title   = {A Mathematical Theory of Communication},
  author  = {Shannon, Claude E.},
  journal = {The Bell System Technical Journal},
  volume  = {27},
  number  = {3},
  pages   = {379--423},
  year    = {1948},
  doi     = {10.1002/j.1538-7305.1948.tb01338.x}
}

@article{bengio2003neural,
  title   = {A Neural Probabilistic Language Model},
  author  = {Bengio, Yoshua and Ducharme, R{\'e}jean and Vincent, Pascal and Janvin, Christian},
  journal = {Journal of Machine Learning Research (JMLR)},
  volume  = {3},
  pages   = {1137--1155},
  year    = {2003}
}

@inproceedings{ho2020diffusion,
  title     = {Denoising Diffusion Probabilistic Models},
  author    = {Ho, Jonathan and Jain, Ajay and Abbeel, Pieter},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2020},
  note      = {arXiv:2006.11239}
}

@book{james2013islr,
  title     = {An Introduction to Statistical Learning: with Applications in R},
  author    = {James, Gareth and Witten, Daniela and Hastie, Trevor and Tibshirani, Robert},
  publisher = {Springer},
  year      = {2013},
  doi       = {10.1007/978-1-4614-7138-7}
}

@article{geman1992bias,
  title   = {Neural Networks and the Bias/Variance Dilemma},
  author  = {Geman, Stuart and Bienenstock, Elie and Doursat, Ren{\'e}},
  journal = {Neural Computation},
  volume  = {4},
  number  = {1},
  pages   = {1--58},
  year    = {1992},
  doi     = {10.1162/neco.1992.4.1.1}
}

@inproceedings{kohavi1995cv,
  title     = {A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection},
  author    = {Kohavi, Ron},
  booktitle = {Proceedings of the 14th International Joint Conference on Artificial Intelligence (IJCAI)},
  pages     = {1137--1145},
  year      = {1995}
}

@book{manning2008ir,
  title     = {Introduction to Information Retrieval},
  author    = {Manning, Christopher D. and Raghavan, Prabhakar and Sch{\"u}tze, Hinrich},
  publisher = {Cambridge University Press},
  year      = {2008}
}

@book{jurafsky2009slp,
  title     = {Speech and Language Processing},
  author    = {Jurafsky, Daniel and Martin, James H.},
  edition   = {2},
  publisher = {Pearson Prentice Hall},
  year      = {2009}
}

@book{bird2009nltk,
  title     = {Natural Language Processing with Python},
  author    = {Bird, Steven and Klein, Ewan and Loper, Edward},
  publisher = {O'Reilly Media},
  year      = {2009}
}

@inproceedings{sennrich2016bpe,
  title     = {Neural Machine Translation of Rare Words with Subword Units},
  author    = {Sennrich, Rico and Haddow, Barry and Birch, Alexandra},
  booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL)},
  year      = {2016},
  note      = {arXiv:1508.07909}
}

@book{zipf1949effort,
  title     = {Human Behavior and the Principle of Least Effort},
  author    = {Zipf, George Kingsley},
  publisher = {Addison-Wesley},
  year      = {1949}
}

@article{porter1980stemming,
  title   = {An Algorithm for Suffix Stripping},
  author  = {Porter, Martin F.},
  journal = {Program},
  volume  = {14},
  number  = {3},
  pages   = {130--137},
  year    = {1980},
  doi     = {10.1108/eb046814}
}

@inproceedings{orengo2001rslp,
  title     = {A Stemming Algorithm for the Portuguese Language},
  author    = {Orengo, Viviane Moreira and Huyck, Christian},
  booktitle = {Proceedings of the 8th International Symposium on String Processing and Information Retrieval (SPIRE)},
  pages     = {186--193},
  year      = {2001},
  doi       = {10.1109/SPIRE.2001.989755}
}

@article{harris1954distributional,
  title   = {Distributional Structure},
  author  = {Harris, Zellig S.},
  journal = {Word},
  volume  = {10},
  number  = {2-3},
  pages   = {146--162},
  year    = {1954},
  doi     = {10.1080/00437956.1954.11659520}
}

@article{sparckjones1972idf,
  title   = {A Statistical Interpretation of Term Specificity and Its Application in Retrieval},
  author  = {Sp{\"a}rck Jones, Karen},
  journal = {Journal of Documentation},
  volume  = {28},
  number  = {1},
  pages   = {11--21},
  year    = {1972},
  doi     = {10.1108/eb026526}
}

@article{salton1988tfidf,
  title   = {Term-Weighting Approaches in Automatic Text Retrieval},
  author  = {Salton, Gerard and Buckley, Christopher},
  journal = {Information Processing and Management},
  volume  = {24},
  number  = {5},
  pages   = {513--523},
  year    = {1988},
  doi     = {10.1016/0306-4573(88)90021-0}
}

@inproceedings{mikolov2013linguistic,
  title     = {Linguistic Regularities in Continuous Space Word Representations},
  author    = {Mikolov, Tomas and Yih, Wen-tau and Zweig, Geoffrey},
  booktitle = {Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT)},
  pages     = {746--751},
  year      = {2013}
}

@inproceedings{levy2014implicit,
  title     = {Neural Word Embedding as Implicit Matrix Factorization},
  author    = {Levy, Omer and Goldberg, Yoav},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2014}
}

@article{deerwester1990lsa,
  title   = {Indexing by Latent Semantic Analysis},
  author  = {Deerwester, Scott and Dumais, Susan T. and Furnas, George W. and Landauer, Thomas K. and Harshman, Richard},
  journal = {Journal of the American Society for Information Science},
  volume  = {41},
  number  = {6},
  pages   = {391--407},
  year    = {1990}
}

@article{elman1990finding,
  title   = {Finding Structure in Time},
  author  = {Elman, Jeffrey L.},
  journal = {Cognitive Science},
  volume  = {14},
  number  = {2},
  pages   = {179--211},
  year    = {1990},
  doi     = {10.1207/s15516709cog1402_1}
}

@article{bengio1994longterm,
  title   = {Learning Long-Term Dependencies with Gradient Descent is Difficult},
  author  = {Bengio, Yoshua and Simard, Patrice and Frasconi, Paolo},
  journal = {IEEE Transactions on Neural Networks},
  volume  = {5},
  number  = {2},
  pages   = {157--166},
  year    = {1994},
  doi     = {10.1109/72.279181}
}

@article{chung2014empirical,
  title   = {Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling},
  author  = {Chung, Junyoung and Gulcehre, Caglar and Cho, KyungHyun and Bengio, Yoshua},
  journal = {arXiv preprint arXiv:1412.3555},
  year    = {2014}
}

@inproceedings{bahdanau2015attention,
  title     = {Neural Machine Translation by Jointly Learning to Align and Translate},
  author    = {Bahdanau, Dzmitry and Cho, Kyunghyun and Bengio, Yoshua},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year      = {2015},
  note      = {arXiv:1409.0473}
}

@article{ba2016layernorm,
  title   = {Layer Normalization},
  author  = {Ba, Jimmy Lei and Kiros, Jamie Ryan and Hinton, Geoffrey E.},
  journal = {arXiv preprint arXiv:1607.06450},
  year    = {2016}
}

@techreport{radford2019gpt2,
  title       = {Language Models are Unsupervised Multitask Learners},
  author      = {Radford, Alec and Wu, Jeffrey and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya},
  institution = {OpenAI},
  year        = {2019}
}

@inproceedings{peters2018elmo,
  title     = {Deep Contextualized Word Representations},
  author    = {Peters, Matthew E. and Neumann, Mark and Iyyer, Mohit and Gardner, Matt and Clark, Christopher and Lee, Kenton and Zettlemoyer, Luke},
  booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)},
  year      = {2018},
  note      = {arXiv:1802.05365}
}

@article{kaplan2020scaling,
  title   = {Scaling Laws for Neural Language Models},
  author  = {Kaplan, Jared and McCandlish, Sam and Henighan, Tom and Brown, Tom B. and Chess, Benjamin and Child, Rewon and Gray, Scott and Radford, Alec and Wu, Jeffrey and Amodei, Dario},
  journal = {arXiv preprint arXiv:2001.08361},
  year    = {2020}
}

@inproceedings{hoffmann2022chinchilla,
  title     = {Training Compute-Optimal Large Language Models},
  author    = {Hoffmann, Jordan and Borgeaud, Sebastian and Mensch, Arthur and others},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2022},
  note      = {arXiv:2203.15556}
}

@article{wei2022emergent,
  title   = {Emergent Abilities of Large Language Models},
  author  = {Wei, Jason and Tay, Yi and Bommasani, Rishi and Raffel, Colin and Zoph, Barret and others},
  journal = {Transactions on Machine Learning Research (TMLR)},
  year    = {2022},
  note    = {arXiv:2206.07682}
}

@inproceedings{christiano2017rlhf,
  title     = {Deep Reinforcement Learning from Human Preferences},
  author    = {Christiano, Paul F. and Leike, Jan and Brown, Tom B. and Martic, Miljan and Legg, Shane and Amodei, Dario},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2017},
  note      = {arXiv:1706.03741}
}

@inproceedings{rafailov2023dpo,
  title     = {Direct Preference Optimization: Your Language Model is Secretly a Reward Model},
  author    = {Rafailov, Rafael and Sharma, Archit and Mitchell, Eric and Ermon, Stefano and Manning, Christopher D. and Finn, Chelsea},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2023},
  note      = {arXiv:2305.18290}
}

@inproceedings{wei2022flan,
  title     = {Finetuned Language Models Are Zero-Shot Learners},
  author    = {Wei, Jason and Bosma, Maarten and Zhao, Vincent Y. and Guu, Kelvin and Yu, Adams Wei and Lester, Brian and Du, Nan and Dai, Andrew M. and Le, Quoc V.},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year      = {2022},
  note      = {arXiv:2109.01652}
}

@inproceedings{hu2021lora,
  title     = {LoRA: Low-Rank Adaptation of Large Language Models},
  author    = {Hu, Edward J. and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Wang, Lu and Chen, Weizhu},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year      = {2022},
  note      = {arXiv:2106.09685}
}

@inproceedings{kojima2022zeroshot,
  title     = {Large Language Models are Zero-Shot Reasoners},
  author    = {Kojima, Takeshi and Gu, Shixiang Shane and Reid, Machel and Matsuo, Yutaka and Iwasawa, Yusuke},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2022},
  note      = {arXiv:2205.11916}
}

@article{liu2023prompt,
  title   = {Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing},
  author  = {Liu, Pengfei and Yuan, Weizhe and Fu, Jinlan and Jiang, Zhengbao and Hayashi, Hiroaki and Neubig, Graham},
  journal = {ACM Computing Surveys},
  volume  = {55},
  number  = {9},
  pages   = {1--35},
  year    = {2023},
  doi     = {10.1145/3560815}
}

@inproceedings{karpukhin2020dpr,
  title     = {Dense Passage Retrieval for Open-Domain Question Answering},
  author    = {Karpukhin, Vladimir and Oguz, Barlas and Min, Sewon and Lewis, Patrick and Wu, Ledell and Edunov, Sergey and Chen, Danqi and Yih, Wen-tau},
  booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year      = {2020},
  note      = {arXiv:2004.04906}
}

@article{johnson2019faiss,
  title   = {Billion-Scale Similarity Search with GPUs},
  author  = {Johnson, Jeff and Douze, Matthijs and J{\'e}gou, Herv{\'e}},
  journal = {IEEE Transactions on Big Data},
  volume  = {7},
  number  = {3},
  pages   = {535--547},
  year    = {2021},
  note    = {arXiv:1702.08734},
  doi     = {10.1109/TBDATA.2019.2921572}
}

@inproceedings{schick2023toolformer,
  title     = {Toolformer: Language Models Can Teach Themselves to Use Tools},
  author    = {Schick, Timo and Dwivedi-Yu, Jane and Dess{\`i}, Roberto and Raileanu, Roberta and Lomeli, Maria and Zettlemoyer, Luke and Cancedda, Nicola and Scialom, Thomas},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2023},
  note      = {arXiv:2302.04761}
}

@inproceedings{park2023generative,
  title     = {Generative Agents: Interactive Simulacra of Human Behavior},
  author    = {Park, Joon Sung and O'Brien, Joseph C. and Cai, Carrie J. and Morris, Meredith Ringel and Liang, Percy and Bernstein, Michael S.},
  booktitle = {Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (UIST)},
  year      = {2023},
  note      = {arXiv:2304.03442}
}

@book{minsky1986society,
  title     = {The Society of Mind},
  author    = {Minsky, Marvin},
  publisher = {Simon \& Schuster},
  year      = {1986}
}

@book{wooldridge2009multiagent,
  title     = {An Introduction to MultiAgent Systems},
  author    = {Wooldridge, Michael},
  edition   = {2},
  publisher = {John Wiley \& Sons},
  year      = {2009}
}

@article{wu2023autogen,
  title   = {AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation},
  author  = {Wu, Qingyun and Bansal, Gagan and Zhang, Jieyu and Wu, Yiran and Li, Beibin and Zhu, Erkang and Jiang, Li and Zhang, Xiaoyun and Zhang, Shaokun and Liu, Jiale and Awadallah, Ahmed Hassan and White, Ryen W. and Burger, Doug and Wang, Chi},
  journal = {arXiv preprint arXiv:2308.08155},
  year    = {2023}
}

@inproceedings{hong2023metagpt,
  title     = {MetaGPT: Meta Programming for a Multi-Agent Collaborative Framework},
  author    = {Hong, Sirui and Zheng, Xiawu and Chen, Jonathan and Cheng, Yuheng and Wang, Jinlin and Zhang, Ceyao and Wang, Zili and Yau, Steven Ka Shing and Lin, Zijuan and Zhou, Liyang and Ran, Chenyu and Xiao, Lingfeng and Wu, Chenglin},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year      = {2024},
  note      = {arXiv:2308.00352}
}

@article{siemens2013learning,
  title   = {Learning Analytics: The Emergence of a Discipline},
  author  = {Siemens, George},
  journal = {American Behavioral Scientist},
  volume  = {57},
  number  = {10},
  pages   = {1380--1400},
  year    = {2013},
  doi     = {10.1177/0002764213498851}
}

@article{romero2010educational,
  title   = {Educational Data Mining: A Review of the State of the Art},
  author  = {Romero, Cristobal and Ventura, Sebastian},
  journal = {IEEE Transactions on Systems, Man, and Cybernetics, Part C},
  volume  = {40},
  number  = {6},
  pages   = {601--618},
  year    = {2010},
  doi     = {10.1109/TSMCC.2010.2053532}
}

@incollection{baker2014educational,
  title     = {Educational Data Mining and Learning Analytics},
  author    = {Baker, Ryan S. J. d. and Inventado, Paul Salvador},
  booktitle = {Learning Analytics: From Research to Practice},
  pages     = {61--75},
  publisher = {Springer},
  year      = {2014},
  doi       = {10.1007/978-1-4614-3305-7_4}
}

@article{corbett1994knowledge,
  title   = {Knowledge Tracing: Modeling the Acquisition of Procedural Knowledge},
  author  = {Corbett, Albert T. and Anderson, John R.},
  journal = {User Modeling and User-Adapted Interaction},
  volume  = {4},
  number  = {4},
  pages   = {253--278},
  year    = {1994},
  doi     = {10.1007/BF01099821}
}

@inproceedings{piech2015deep,
  title     = {Deep Knowledge Tracing},
  author    = {Piech, Chris and Bassen, Jonathan and Huang, Jonathan and Ganguli, Surya and Sahami, Mehran and Guibas, Leonidas J. and Sohl-Dickstein, Jascha},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2015},
  note      = {arXiv:1506.05908}
}

@article{brusilovsky2001adaptive,
  title   = {Adaptive Hypermedia},
  author  = {Brusilovsky, Peter},
  journal = {User Modeling and User-Adapted Interaction},
  volume  = {11},
  number  = {1-2},
  pages   = {87--110},
  year    = {2001},
  doi     = {10.1023/A:1011143116306}
}

@article{vanlehn2011relative,
  title   = {The Relative Effectiveness of Human Tutoring, Intelligent Tutoring Systems, and Other Tutoring Systems},
  author  = {VanLehn, Kurt},
  journal = {Educational Psychologist},
  volume  = {46},
  number  = {4},
  pages   = {197--221},
  year    = {2011},
  doi     = {10.1080/00461520.2011.611369}
}

@article{kasneci2023chatgpt,
  title   = {ChatGPT for Good? On Opportunities and Challenges of Large Language Models for Education},
  author  = {Kasneci, Enkelejda and Sessler, Kathrin and K{\"u}chemann, Stefan and Bannert, Maria and Dementieva, Daryna and Fischer, Frank and Gasser, Urs and Groh, Georg and G{\"u}nnemann, Stephan and H{\"u}llermeier, Eyke and others},
  journal = {Learning and Individual Differences},
  volume  = {103},
  pages   = {102274},
  year    = {2023},
  doi     = {10.1016/j.lindif.2023.102274}
}