{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T08:31:25Z","timestamp":1782894685113,"version":"3.54.5"},"reference-count":97,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"funder":[{"name":"PRIN 2022 PNRR project","award":["P2022MPFRT"],"award-info":[{"award-number":["P2022MPFRT"]}]},{"name":"European Union\u2014Next Generation EU"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Evol. Learn. Optim."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>Curriculum learning (CL) consists in using a diverse set of user-provided test cases, with varying levels of difficulty and organized in a suitable progression, for learning a policy. The quality of test cases is important to allow optimization techniques as genetic programming (GP) to solve policy search problems. In this work, we evaluate large language models (LLMs) as providers of test cases for GP-based policy search. We consider two policy search tasks, a single-player and a multi-player game, and four LLMs differing in complexity and specialization, which we prompt in order to generate suitable test cases for the two games. We experimentally assess the intrinsic quality of LLM-generated test cases and their utility when inserted in a curriculum consumed by a GP optimization. We evaluate the robustness of the approach with respect to the way cases are scheduled in curricula and with respect to the policy representation, for which we use both graphs and linear programs evolved by GP. We observe that the effectiveness of LLM-assisted CL depends on both the choice of LLM and the design of the prompting and scheduling strategies. These findings highlight important considerations for leveraging LLMs in automated curriculum design for GP-based optimization.<\/jats:p>","DOI":"10.1145\/3772718","type":"journal-article","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T12:48:26Z","timestamp":1761914906000},"page":"1-37","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Policy Search through Genetic Programming and LLM-assisted Curriculum Learning"],"prefix":"10.1145","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7782-0969","authenticated-orcid":false,"given":"Steven","family":"Jorgensen","sequence":"first","affiliation":[{"name":"MIT CSAIL, Cambridge, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3535-9748","authenticated-orcid":false,"given":"Giorgia","family":"Nadizar","sequence":"additional","affiliation":[{"name":"Dipartimento di Ingegneria e Architettura, University of Trieste, Trieste, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7623-8419","authenticated-orcid":false,"given":"Gloria","family":"Pietropolli","sequence":"additional","affiliation":[{"name":"Dipartimento di Matematica, Informatica e Geoscienze, University of Trieste, Trieste, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6312-7728","authenticated-orcid":false,"given":"Luca","family":"Manzoni","sequence":"additional","affiliation":[{"name":"Dipartimento di Matematica, Informatica e Geoscienze, University of Trieste, Trieste, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5652-2113","authenticated-orcid":false,"given":"Eric","family":"Medvet","sequence":"additional","affiliation":[{"name":"Dipartimento di Ingegneria e Architettura, University of Trieste, Trieste, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6923-8445","authenticated-orcid":false,"given":"Una-May","family":"O\u2019Reilly","sequence":"additional","affiliation":[{"name":"MIT CSAIL, Cambridge, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2153-3506","authenticated-orcid":false,"given":"Erik","family":"Hemberg","sequence":"additional","affiliation":[{"name":"MIT CSAIL, Cambridge, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"e_1_3_2_2_1","volume-title":"Using Genetic Programming to Evolve a Connect-4 Game Player","author":"Abdelsadek Mohamed F.","unstructured":"Mohamed F. Abdelsadek. n.d. Using Genetic Programming to Evolve a Connect-4 Game Player. Department of Computer Science, Columbia University. Retrieved from https:\/\/www.cs.columbia.edu\/~evs\/ml\/MLfinalproj\/mohamed\/connect4.html"},{"key":"e_1_3_2_3_1","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et al. 2023. GPT-4 technical report. arXiv:2303.08774. Retrieved from https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.26481\/dis.19940923la"},{"key":"e_1_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3520304.3528766"},{"key":"e_1_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA200717"},{"key":"e_1_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-019-09359-z"},{"key":"e_1_3_2_10_1","volume-title":"Basic Concepts of Linear Genetic Programming","author":"Brameier Markus F.","year":"2007","unstructured":"Markus F. Brameier and Wolfgang Banzhaf. 2007. Basic Concepts of Linear Genetic Programming. Springer."},{"key":"e_1_3_2_11_1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 33, 1877\u20131901.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.31235\/osf.io\/sthwk_v2"},{"key":"e_1_3_2_13_1","first-page":"345","volume-title":"Proceedings of the European Symposium on Artificial Neural Networks","author":"Cofala Tim","year":"2020","unstructured":"Tim Cofala, Lars Elend, and Oliver Kramer. 2020. Tournament selection improves cartesian genetic programming for Atari games. In Proceedings of the European Symposium on Artificial Neural Networks, 345\u2013350."},{"key":"e_1_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3520304.3528897"},{"key":"e_1_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-2594-7_59"},{"key":"e_1_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2018.8477698"},{"key":"e_1_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3638530.3654347"},{"key":"e_1_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3712256.3726332"},{"key":"e_1_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-019-09363-3"},{"key":"e_1_3_2_20_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The Llama 3 Herd of models. arXiv:2407.21783. Retrieved from https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85845-4_23"},{"key":"e_1_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(93)90058-4"},{"key":"e_1_3_2_23_1","unstructured":"Maxence Faldor Jenny Zhang Antoine Cully and Jeff Clune. 2024. OMNI-EPIC: Open-endedness via models of human notions of interestingness with environments programmed in code. arXiv:2405.15568. Retrieved from https:\/\/arxiv.org\/abs\/2405.15568"},{"key":"e_1_3_2_24_1","first-page":"482","volume-title":"Proceedings of the Conference on Robot Learning","author":"Florensa Carlos","year":"2017","unstructured":"Carlos Florensa, David Held, Markus Wulfmeier, Michael Zhang, and Pieter Abbeel. 2017. Reverse curriculum generation for reinforcement learning. In Proceedings of the Conference on Robot Learning. PMLR, 482\u2013495."},{"key":"e_1_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-021-09413-9"},{"key":"e_1_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321831"},{"key":"e_1_3_2_27_1","volume-title":"Reinforcement Learning in Board Games","author":"Ghory Imran","year":"2004","unstructured":"Imran Ghory. 2004. Reinforcement Learning in Board Games. Technical Report 105. Department of Computer Science, University of Bristol."},{"key":"e_1_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-30229-9_49"},{"key":"e_1_3_2_29_1","unstructured":"Qingyan Guo Rui Wang Junliang Guo Bei Li Kaitao Song Xu Tan Guoqing Liu Jiang Bian and Yujiu Yang. 2023. Connecting large language models with evolutionary algorithms yields powerful prompt optimizers. arXiv:2309.08532. Retrieved from https:\/\/arxiv.org\/abs\/2309.08532"},{"key":"e_1_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_9"},{"key":"e_1_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41965-024-00172-x"},{"key":"e_1_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-024-09494-2"},{"key":"e_1_3_2_33_1","unstructured":"Dong Huang Qingwen Bu Jie Zhang Xiaofei Xie Junjie Chen and Heming Cui. 2023. Bias assessment and mitigation in LLM-based code generation. arXiv:2309.14345. Retrieved from https:\/\/arxiv.org\/abs\/2309.14345"},{"key":"e_1_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654918"},{"key":"e_1_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3638529.3654056"},{"key":"e_1_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45984-7_8"},{"key":"e_1_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2188528"},{"key":"e_1_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55696-3_5"},{"key":"e_1_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3071178.3071303"},{"key":"e_1_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341979"},{"key":"e_1_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-021-09418-4"},{"key":"e_1_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00175355"},{"key":"e_1_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-3814-8_11"},{"key":"e_1_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2022.101223"},{"key":"e_1_3_2_45_1","unstructured":"Kenneth Li Aspen K. Hopkins David Bau Fernanda Vi\u00e9gas Hanspeter Pfister and Martin Wattenberg. 2022. Emergent world representations: Exploring a sequence model trained on a synthetic task. arXiv:2210.13382. Retrieved from https:\/\/arxiv.org\/abs\/2210.13382"},{"issue":"6","key":"e_1_3_2_46_1","first-page":"e40895","article-title":"ChatDoctor: A medical chat model fine-tuned on a large language model meta-AI (LLaMA) using medical domain knowledge","volume":"15","author":"Li Yunxiang","year":"2023","unstructured":"Yunxiang Li, Zihan Li, Kai Zhang, Ruilong Dan, Steve Jiang, and You Zhang. 2023. ChatDoctor: A medical chat model fine-tuned on a large language model meta-AI (LLaMA) using medical domain knowledge. Cureus 15, 6 (2023), e40895.","journal-title":"Cureus"},{"key":"e_1_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.478"},{"key":"e_1_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207427"},{"key":"e_1_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5699"},{"key":"e_1_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111654"},{"key":"e_1_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-88464-5"},{"key":"e_1_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-019-09360-6"},{"key":"e_1_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-46239-2_9"},{"key":"e_1_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"key":"e_1_3_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463147"},{"key":"e_1_3_2_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02056-8_10"},{"key":"e_1_3_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3638529.3653987"},{"key":"e_1_3_2_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56957-9_5"},{"key":"e_1_3_2_59_1","article-title":"Enhancing adaptability in embodied agents: A multi-quality-diversity approach","author":"Nadizar Giorgia","year":"2025","unstructured":"Giorgia Nadizar, Eric Medvet, and Dennis G. Wilson. 2025. Enhancing adaptability in embodied agents: A multi-quality-diversity approach. IEEE Transactions on Evolutionary Computation (2025). DOI: https:\/\/ieeexplore.ieee.org\/document\/11119655","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"e_1_3_2_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41965-023-00125-w"},{"key":"e_1_3_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3643688"},{"key":"e_1_3_2_62_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455897"},{"key":"e_1_3_2_63_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/353"},{"issue":"4","key":"e_1_3_2_64_1","first-page":"1637","article-title":"Alpha-beta pruning in mini-max algorithm\u2014An optimized approach for a Connect-4 game","volume":"5","author":"Nasa Rijul","year":"2018","unstructured":"Rijul Nasa, Rishabh Didwania, Shubhranil Maji, and Vipul Kumar. 2018. Alpha-beta pruning in mini-max algorithm\u2014An optimized approach for a Connect-4 game. International Research Journal of Engineering and Technology 5, 4 (2018), 1637\u20131641.","journal-title":"International Research Journal of Engineering and Technology"},{"key":"e_1_3_2_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-20525-5_13"},{"key":"e_1_3_2_66_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1119"},{"key":"e_1_3_2_67_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06924-6"},{"key":"e_1_3_2_68_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"e_1_3_2_69_1","article-title":"Data parameters: A new family of parameters for learning a differentiable curriculum","volume":"32","author":"Saxena Shreyas","year":"2019","unstructured":"Shreyas Saxena, Oncel Tuzel, and Dennis DeCoste. 2019. Data parameters: A new family of parameters for learning a differentiable curriculum. In Proceedings of the Advances in Neural Information Processing Systems, Vol 32.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_70_1","first-page":"236","volume-title":"Proceedings of the VII Brazilian Symposium on Neural Networks (SBRN \u201902)","author":"Schneider Marvin Oliver","year":"2002","unstructured":"Marvin Oliver Schneider and J. L. Garcia Rosa. 2002. Neural connect 4\u2014A connectionist approach to the game. In Proceedings of the VII Brazilian Symposium on Neural Networks (SBRN \u201902). IEEE, 236\u2013241."},{"key":"e_1_3_2_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"e_1_3_2_72_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-31989-4_13"},{"key":"e_1_3_2_73_1","first-page":"12","article-title":"Artificial neural nets applied to strategic games","volume":"5","author":"Sommerlund Peer","year":"1996","unstructured":"Peer Sommerlund. 1996. Artificial neural nets applied to strategic games. Unpublished, Last Access 5 (1996), 12.","journal-title":"Unpublished, Last Access"},{"key":"e_1_3_2_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"e_1_3_2_75_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01611-x"},{"key":"e_1_3_2_76_1","volume-title":"Synthesizing Board Evaluation Functions for Connect-4 Using Machine Learning Techniques","author":"Stenmark Martin","year":"2005","unstructured":"Martin Stenmark. 2005. Synthesizing Board Evaluation Functions for Connect-4 Using Machine Learning Techniques. Master\u2019s thesis. \u00d8stfold University College, Norway."},{"key":"e_1_3_2_77_1","article-title":"MarioGPT: Open-ended Text2Level generation through large language models","volume":"36","author":"Sudhakaran Shyam","year":"2024","unstructured":"Shyam Sudhakaran, Miguel Gonz\u00e1lez-Duque, Matthias Freiberger, Claire Glanois, Elias Najarro, and Sebastian Risi. 2024. MarioGPT: Open-ended Text2Level generation through large language models. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 36.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_78_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1486"},{"key":"e_1_3_2_79_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32937-1_19"},{"key":"e_1_3_2_80_1","volume-title":"Interaction and Coevolution","author":"Thompson John N.","year":"2014","unstructured":"John N. Thompson. 2014. Interaction and Coevolution. University of Chicago Press."},{"key":"e_1_3_2_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582437.3587211"},{"key":"e_1_3_2_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2010.5586133"},{"key":"e_1_3_2_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2009.5286481"},{"key":"e_1_3_2_84_1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v34i3.2492"},{"key":"e_1_3_2_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3712256.3726400"},{"key":"e_1_3_2_86_1","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 30.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_87_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02056-8_18"},{"key":"e_1_3_2_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321799"},{"issue":"9","key":"e_1_3_2_89_1","first-page":"4555","article-title":"A survey on curriculum learning","volume":"44","author":"Wang Xin","year":"2021","unstructured":"Xin Wang, Yudong Chen, and Wenwu Zhu. 2021. A survey on curriculum learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 9 (2021), 4555\u20134576.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_90_1","first-page":"5238","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Weinshall Daphna","year":"2018","unstructured":"Daphna Weinshall, Gad Cohen, and Dan Amir. 2018. Curriculum learning by transfer learning: Theory and experiments with deep networks. In Proceedings of the International Conference on Machine Learning (ICML). PMLR, 5238\u20135246."},{"key":"e_1_3_2_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205578"},{"key":"e_1_3_2_92_1","unstructured":"Dennis G. Wilson Julian F. Miller Sylvain Cussat-Blanc and Herv\u00e9 Luga. 2018b. Positional cartesian genetic programming. arXiv:1810.04119. Retrieved from https:\/\/arxiv.org\/abs\/1810.04119"},{"key":"e_1_3_2_93_1","unstructured":"Xingyu Wu Sheng-Hao Wu Jibin Wu Liang Feng and Kay Chen Tan. 2024. Evolutionary computation in the era of large language model: Survey and roadmap. arXiv:2401.10034. Retrieved from https:\/\/arxiv.org\/abs\/2401.10034"},{"key":"e_1_3_2_94_1","first-page":"292","volume-title":"Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING \u201923)","author":"Yeh Kai-Ching","year":"2023","unstructured":"Kai-Ching Yeh, Jou-An Chi, Da-Chen Lian, and Shu-Kai Hsieh. 2023. Evaluating interfaced LLM bias. In Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING \u201923), 292\u2013299."},{"key":"e_1_3_2_95_1","unstructured":"Abhay Zala Jaemin Cho Han Lin Jaehong Yoon and Mohit Bansal. 2024. EnvGen: Generating and adapting environments via LLMs for training embodied agents. arXiv:2403.12014. Retrieved from https:\/\/arxiv.org\/abs\/2403.12014"},{"key":"e_1_3_2_96_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09894-7"},{"key":"e_1_3_2_97_1","unstructured":"Yue Zhang Yafu Li Leyang Cui Deng Cai Lemao Liu Tingchen Fu Xinting Huang Enbo Zhao Yu Zhang Yulong Chen et al. 2023. Siren\u2019s song in the AI ocean: A survey on hallucination in large language models. arXiv:2309.01219. Retrieved from https:\/\/arxiv.org\/abs\/2309.01219"},{"key":"e_1_3_2_98_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv:2303.18223. Retrieved from https:\/\/arxiv.org\/abs\/2303.18223"}],"container-title":["ACM Transactions on Evolutionary Learning and Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772718","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T06:30:20Z","timestamp":1782887420000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772718"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":97,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3772718"],"URL":"https:\/\/doi.org\/10.1145\/3772718","relation":{},"ISSN":["2688-299X","2688-3007"],"issn-type":[{"value":"2688-299X","type":"print"},{"value":"2688-3007","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]},"assertion":[{"value":"2024-12-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}