{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:59:04Z","timestamp":1774022344538,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","funder":[{"name":"EPSRC Centre for Doctoral Training in Natural Language Processing","award":["EP\/S022481\/1"],"award-info":[{"award-number":["EP\/S022481\/1"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,10]]},"DOI":"10.1145\/3721238.3730742","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T08:42:43Z","timestamp":1753260163000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CueTip: An Interactive and Explainable Physics-aware Pool Assistant"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2437-5154","authenticated-orcid":false,"given":"Sean","family":"Memery","sequence":"first","affiliation":[{"name":"University of Edinburgh, Edinburgh, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8776-4331","authenticated-orcid":false,"given":"Kevin","family":"Denamgana\u00ef","sequence":"additional","affiliation":[{"name":"University of Edinburgh, Edinburgh, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7355-7975","authenticated-orcid":false,"given":"Jiaxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Lightspeed Studios, London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7153-8509","authenticated-orcid":false,"given":"Zehai","family":"Tu","sequence":"additional","affiliation":[{"name":"Lightspeed Studios, London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0709-4877","authenticated-orcid":false,"given":"Yiwen","family":"Guo","sequence":"additional","affiliation":[{"name":"Independent, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7302-4383","authenticated-orcid":false,"given":"Kartic","family":"Subr","sequence":"additional","affiliation":[{"name":"University of Edinburgh, Edinburgh, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_3_3_2_2_1","unstructured":"AI@Meta. 2024. Llama 3 Model Card. (2024). https:\/\/github.com\/meta-llama\/llama3\/blob\/main\/MODEL_CARD.md"},{"key":"e_1_3_3_2_3_1","volume-title":"The Illustrated Principles of Pool and Billiards","author":"Alciatore D.G.","year":"2004","unstructured":"D.G. Alciatore. 2004. The Illustrated Principles of Pool and Billiards. Sterling. https:\/\/books.google.co.uk\/books?id=gYU_cpeFXhwC"},{"key":"e_1_3_3_2_4_1","unstructured":"Mohammad Alian. 2003. Roboshark : a gantry pool player robot. https:\/\/api.semanticscholar.org\/CorpusID:10384485"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"crossref","unstructured":"Christopher Archibald Alon Altman Michael\u00a0A. Greenspan and Yoav Shoham. 2010. Computational Pool: A New Challenge for Game Theory Pragmatics. AI Mag. 31 (2010) 33\u201341. https:\/\/api.semanticscholar.org\/CorpusID:1427129","DOI":"10.1609\/aimag.v31i4.2312"},{"key":"e_1_3_3_2_6_1","volume-title":"International Joint Conference on Artificial Intelligence","author":"Archibald Christopher","year":"2009","unstructured":"Christopher Archibald, Alon Altman, and Yoav Shoham. 2009. Analysis of a Winning Computational Billiards Player. In International Joint Conference on Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:61081368"},{"key":"e_1_3_3_2_7_1","volume-title":"International Conference on Language Resources and Evaluation","author":"Arsevska Elena","year":"2016","unstructured":"Elena Arsevska, Mathieu Roche, Sylvain Falala, Renaud Lancelot, David Chavernac, Pascal Hendrikx, and Barbara Dufour. 2016. Monitoring Disease Outbreak Events on the Web Using Text-mining Approach and Domain Expert Knowledge. In International Conference on Language Resources and Evaluation. https:\/\/api.semanticscholar.org\/CorpusID:31600041"},{"key":"e_1_3_3_2_8_1","unstructured":"Renee Baillargeon. 1995. Physical reasoning in infancy. The cognitive neurosciences (1995) 181\u2013204."},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"crossref","unstructured":"Renee Baillargeon Elizabeth\u00a0S Spelke and Stanley Wasserman. 1985. Object permanence in five-month-old infants. Cognition 20 3 (1985) 191\u2013208.","DOI":"10.1016\/0010-0277(85)90008-3"},{"key":"e_1_3_3_2_10_1","unstructured":"Vahid Balazadeh Mohammadmehdi Ataei Hyunmin Cheong Amir\u00a0Hosein Khasahmadi and Rahul\u00a0G. Krishnan. 2024. Synthetic Vision: Training Vision-Language Models to Understand Physics. arxiv:https:\/\/arXiv.org\/abs\/2412.08619\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2412.08619"},{"key":"e_1_3_3_2_11_1","unstructured":"Peter Battaglia Razvan Pascanu Matthew Lai Danilo Jimenez\u00a0Rezende et\u00a0al. 2016. Interaction networks for learning about objects relations and physics. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"crossref","unstructured":"Peter\u00a0W Battaglia Jessica\u00a0B Hamrick and Joshua\u00a0B Tenenbaum. 2013. Simulation as an engine of physical scene understanding. Proceedings of the National Academy of Sciences 110 45 (2013) 18327\u201318332.","DOI":"10.1073\/pnas.1306572110"},{"key":"e_1_3_3_2_13_1","unstructured":"Anoop Cherian Radu Corcodel Siddarth Jain and Diego Romeres. 2024. LLMPhy: Complex Physical Reasoning Using Large Language Models and World Models. arxiv:https:\/\/arXiv.org\/abs\/2411.08027\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2411.08027"},{"key":"e_1_3_3_2_14_1","unstructured":"Yu-Neng Chuang Guanchu Wang Chia yuan Chang Ruixiang Tang Fan Yang Mengnan Du Xuanting Cai and Xia Hu. 2024. Large Language Models As Faithful Explainers. ArXiv abs\/2402.04678 (2024). https:\/\/api.semanticscholar.org\/CorpusID:271303565"},{"key":"e_1_3_3_2_15_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano et\u00a0al. 2021. Training verifiers to solve math word problems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.14168 (2021)."},{"key":"e_1_3_3_2_16_1","unstructured":"Jingzhe Ding Yan Cen and Xinyuan Wei. 2023. Using Large Language Model to Solve and Explain Physics Word Problems Approaching Human Level. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.08182 (2023)."},{"key":"e_1_3_3_2_17_1","volume-title":"Computers and Games","author":"Dussault Jean-Pierre","year":"2006","unstructured":"Jean-Pierre Dussault and Jean-Fran\u00e7ois Landry. 2006. Optimization of a Billiard Player - Tactical Play. In Computers and Games. https:\/\/api.semanticscholar.org\/CorpusID:15820129"},{"key":"e_1_3_3_2_18_1","unstructured":"Linxi Fan Guanzhi Wang Yunfan Jiang Ajay Mandlekar Yuncong Yang Haoyi Zhu Andrew Tang De-An Huang Yuke Zhu and Anima Anandkumar. 2022. MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge. arxiv:https:\/\/arXiv.org\/abs\/2206.08853\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2206.08853"},{"key":"e_1_3_3_2_19_1","unstructured":"Weixi Feng Wanrong Zhu Tsu-jui Fu Varun Jampani Arjun Akula Xuehai He Sugato Basu Xin\u00a0Eric Wang and William\u00a0Yang Wang. 2024. Layoutgpt: Compositional visual planning and generation with large language models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"crossref","unstructured":"Javier Ferrando Gerard\u00a0I. G\u00e1llego and Marta\u00a0Ruiz Costa-juss\u00e0. 2022. Measuring the Mixing of Contextual Information in the Transformer. ArXiv abs\/2203.04212 (2022). https:\/\/api.semanticscholar.org\/CorpusID:247315171","DOI":"10.18653\/v1\/2022.emnlp-main.595"},{"key":"e_1_3_3_2_21_1","unstructured":"Katerina Fragkiadaki Pulkit Agrawal Sergey Levine and Jitendra Malik. 2015. Learning Visual Predictive Models of Physics for Playing Billiards. arXiv: Computer Vision and Pattern Recognition (2015). https:\/\/api.semanticscholar.org\/CorpusID:6981893"},{"key":"e_1_3_3_2_22_1","unstructured":"Isabel\u00a0O Gallegos Ryan\u00a0A Rossi Joe Barrow Md\u00a0Mehrab Tanjim Sungchul Kim Franck Dernoncourt Tong Yu Ruiyi Zhang and Nesreen\u00a0K Ahmed. 2024. Bias and fairness in large language models: A survey. Computational Linguistics (2024) 1\u201379."},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"crossref","unstructured":"Michael\u00a0A. Greenspan Joseph Lam Marc Godard Imran Zaidi Sam Jordan William\u00a0H. Leckie Ken Anderson and Donna\u00a0C. Dupuis. 2008. Toward a Competitive Pool-Playing Robot. Computer 41 (2008). https:\/\/api.semanticscholar.org\/CorpusID:17191082","DOI":"10.1109\/MC.2008.33"},{"key":"e_1_3_3_2_24_1","unstructured":"Dan Hendrycks Collin Burns Saurav Kadavath Akul Arora Steven Basart Eric Tang Dawn Song and Jacob Steinhardt. 2021. Measuring mathematical problem solving with the math dataset. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2103.03874 (2021)."},{"key":"e_1_3_3_2_25_1","first-page":"1769","volume-title":"Conference on Robot Learning","author":"Huang Wenlong","year":"2023","unstructured":"Wenlong Huang, Fei Xia, Ted Xiao, Harris Chan, Jacky Liang, Pete Florence, Andy Zeng, Jonathan Tompson, Igor Mordatch, Yevgen Chebotar, et\u00a0al. 2023. Inner Monologue: Embodied Reasoning through Planning with Language Models. In Conference on Robot Learning. PMLR, 1769\u20131782."},{"key":"e_1_3_3_2_26_1","unstructured":"HuggingFace. 2025. Meta-Llama 3.1 70B Instruct. https:\/\/huggingface.co\/meta-llama\/Meta-Llama-3.1-70B-Instruct. Accessed: 2025-01-23."},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/696"},{"key":"e_1_3_3_2_28_1","unstructured":"Subbarao Kambhampati Karthik Valmeekam Lin Guan Kaya Stechly Mudit Verma Siddhant Bhambri Lucas Saldyt and Anil Murthy. 2024. LLMs Can\u2019t Plan But Can Help Planning in LLM-Modulo Frameworks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.01817 (2024)."},{"key":"e_1_3_3_2_29_1","unstructured":"Omar Khattab Arnav Singhvi Paridhi Maheshwari Zhiyuan Zhang Keshav Santhanam Sri Vardhamanan Saiful Haq Ashutosh Sharma Thomas\u00a0T. Joshi Hanna Moazam Heather Miller Matei Zaharia and Christopher Potts. 2024. DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines. The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"crossref","unstructured":"Evan Kiefl. 2024. Pooltool: A Python package for realistic billiards simulation. Journal of Open Source Software 9 101 (2024) 7301. https:\/\/doi.org\/10.21105\/joss.07301","DOI":"10.21105\/joss.07301"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"crossref","unstructured":"In-Kyeong Kim and Elizabeth\u00a0S Spelke. 1999. Perception and understanding of effects of gravity and inertia on object motion. Developmental Science 2 3 (1999) 339\u2013362.","DOI":"10.1111\/1467-7687.00080"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"crossref","unstructured":"James\u00a0R Kubricht Keith\u00a0J Holyoak and Hongjing Lu. 2017. Intuitive physics: Current research and controversies. Trends in cognitive sciences 21 10 (2017) 749\u2013759.","DOI":"10.1016\/j.tics.2017.06.002"},{"key":"e_1_3_3_2_33_1","unstructured":"Tamera Lanham Anna Chen Ansh Radhakrishnan Benoit Steiner Carson Denison Danny Hernandez Dustin Li Esin Durmus Evan Hubinger Jackson Kernion et\u00a0al. 2023. Measuring faithfulness in chain-of-thought reasoning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.13702 (2023)."},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"crossref","unstructured":"Robert\u00a0K. Lindsay Bruce\u00a0G. Buchanan Edward\u00a0A. Feigenbaum and Joshua Lederberg. 1993. DENDRAL: A case study of the first expert system for scientific hypothesis formation. Artificial Intelligence 61 2 (1993) 209\u2013261. https:\/\/doi.org\/10.1016\/0004-3702(93)90068-M","DOI":"10.1016\/0004-3702(93)90068-M"},{"key":"e_1_3_3_2_35_1","unstructured":"Ruibo Liu Jason Wei Shixiang\u00a0Shane Gu Te-Yen Wu Soroush Vosoughi Claire Cui Denny Zhou and Andrew\u00a0M. Dai. 2022. Mind\u2019s Eye: Grounded Language Model Reasoning through Simulation. ArXiv abs\/2210.05359 (2022). https:\/\/api.semanticscholar.org\/CorpusID:252815535"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.591"},{"key":"e_1_3_3_2_37_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lu Pan","year":"2024","unstructured":"Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, and Jianfeng Gao. 2024. MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_2_38_1","volume-title":"Neural Information Processing Systems","author":"Lundberg Scott\u00a0M.","year":"2017","unstructured":"Scott\u00a0M. Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In Neural Information Processing Systems. https:\/\/api.semanticscholar.org\/CorpusID:21889700"},{"key":"e_1_3_3_2_39_1","unstructured":"Haoyan Luo and Lucia Specia. 2024. From Understanding to Utilization: A Survey on Explainability for Large Language Models. ArXiv abs\/2401.12874 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267095032"},{"key":"e_1_3_3_2_40_1","unstructured":"Bohan Lyu Yadi Cao Duncan Watson-Parris Leon Bergen Taylor Berg-Kirkpatrick and Rose Yu. 2024. Adapting While Learning: Grounding LLMs for Scientific Problems with Intelligent Tool Usage Adaptation. ArXiv abs\/2411.00412 (2024). https:\/\/api.semanticscholar.org\/CorpusID:273798174"},{"key":"e_1_3_3_2_41_1","unstructured":"Matteo\u00a0G. Mecattaf Ben Slater Marko Tevsi\u2019c Jonathan Prunty Konstantinos Voudouris and Lucy\u00a0G. Cheke. 2024. A little less conversation a little more action please: Investigating the physical common-sense of LLMs in a 3D embodied environment. https:\/\/api.semanticscholar.org\/CorpusID:273695554"},{"key":"e_1_3_3_2_42_1","unstructured":"Sean Memery Mirella Lapata and Kartic Subr. 2024. SimLM: Can Language Models Infer Parameters of Physical Systems? arxiv:https:\/\/arXiv.org\/abs\/2312.14215\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2312.14215"},{"key":"e_1_3_3_2_43_1","unstructured":"NVIDIA : Alisson Azzolini Hannah Brandon Prithvijit Chattopadhyay Huayu Chen Jinju Chu Yin Cui Jenna Diamond Yifan Ding Francesco Ferroni Rama Govindaraju Jinwei Gu Siddharth Gururani Imad\u00a0El Hanafi Zekun Hao Jacob Huffman Jingyi Jin Brendan Johnson Rizwan Khan George Kurian Elena Lantz Nayeon Lee Zhaoshuo Li Xuan Li Tsung-Yi Lin Yen-Chen Lin Ming-Yu Liu Alice Luo Andrew Mathau Yun Ni Lindsey Pavao Wei Ping David\u00a0W. Romero Misha Smelyanskiy Shuran Song Lyne Tchapmi Andrew\u00a0Z. Wang Boxin Wang Haoxiang Wang Fangyin Wei Jiashu Xu Yao Xu Xiaodong Yang Zhuolin Yang Xiaohui Zeng and Zhe Zhang. 2025. Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning. arxiv:https:\/\/arXiv.org\/abs\/2503.15558\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2503.15558"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"crossref","unstructured":"Luis\u00a0S Piloto Ari Weinstein Peter Battaglia and Matthew Botvinick. 2022. Intuitive physics learning in a deep-learning model inspired by developmental psychology. Nature human behaviour 6 9 (2022) 1257\u20131267.","DOI":"10.1038\/s41562-022-01394-8"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"crossref","unstructured":"Giulia Polverini and Bor Gregorcic. 2024. How understanding large language models can inform the use of ChatGPT in physics education. European Journal of Physics 45 2 (Jan. 2024) 025701. https:\/\/doi.org\/10.1088\/1361-6404\/ad1420","DOI":"10.1088\/1361-6404\/ad1420"},{"key":"e_1_3_3_2_46_1","unstructured":"Prolific. 2025. Prolific. https:\/\/prolific.com\/ Accessed: 2025-01-10."},{"key":"e_1_3_3_2_47_1","volume-title":"Expert Systems","author":"Ryan Darrel","year":"2017","unstructured":"Darrel Ryan (Ed.). 2017. Expert Systems. Nova Science, Hauppauge, NY."},{"key":"e_1_3_3_2_48_1","unstructured":"Shu Sang and William Cheung. 1994. Automating skills using a robot snooker player. https:\/\/api.semanticscholar.org\/CorpusID:62491524"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"crossref","unstructured":"Julio Silva-Rodr\u00edguez Hadi Chakor Riadh Kobbi Jos\u00e9 Dolz and Ismail\u00a0Ben Ayed. 2023. A Foundation LAnguage-Image model of the Retina (FLAIR): Encoding expert knowledge in text supervision. Medical image analysis 99 (2023) 103357. https:\/\/api.semanticscholar.org\/CorpusID:260899927","DOI":"10.1016\/j.media.2024.103357"},{"key":"e_1_3_3_2_50_1","unstructured":"Kevin Smith Lingjie Mei Shunyu Yao Jiajun Wu Elizabeth Spelke Josh Tenenbaum and Tomer Ullman. 2019. Modeling expectation violation in intuitive physics with coarse probabilistic object representations. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"crossref","unstructured":"Michael Smith. 2007. PickPocket: A computer billiards shark. Artif. Intell. 171 (2007) 1069\u20131091. https:\/\/api.semanticscholar.org\/CorpusID:7180834","DOI":"10.1016\/j.artint.2007.04.011"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"crossref","unstructured":"Elizabeth\u00a0S Spelke Karen Breinlinger Janet Macomber and Kristen Jacobson. 1992. Origins of knowledge. Psychological review 99 4 (1992) 605.","DOI":"10.1037\/\/0033-295X.99.4.605"},{"key":"e_1_3_3_2_53_1","volume-title":"International Conference on Machine Learning","author":"Sundararajan Mukund","year":"2017","unstructured":"Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic Attribution for Deep Networks. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:16747630"},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"crossref","unstructured":"Kuei\u00a0Gu Tung Sheng\u00a0Wen Wang Wen-Kai Tai Der-Lor Way and Chinchen Chang. 2019. Toward Human-like Billiard AI Bot Based on Backward Induction and Machine Learning. 2019 IEEE Symposium Series on Computational Intelligence (SSCI) (2019) 924\u2013932. https:\/\/api.semanticscholar.org\/CorpusID:211243863","DOI":"10.1109\/SSCI44817.2019.9003085"},{"key":"e_1_3_3_2_56_1","unstructured":"Miles Turpin Julian Michael Ethan Perez and Samuel Bowman. 2024. Language models don\u2019t always say what they think: unfaithful explanations in chain-of-thought prompting. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_2_57_1","doi-asserted-by":"crossref","unstructured":"Karthik Valmeekam Matthew Marquez Sarath Sreedharan and Subbarao Kambhampati. 2023. On the planning abilities of large language models-a critical investigation. Advances in Neural Information Processing Systems 36 (2023) 75993\u201376005.","DOI":"10.52202\/075280-3320"},{"key":"e_1_3_3_2_58_1","unstructured":"Konstantinos Voudouris Niall Donnelly Danaja Rutar Ryan Burnell John Burden Jos\u00e9 Hern\u00e1ndez-Orallo and Lucy\u00a0G Cheke. 2022. Evaluating object permanence in embodied agents using the animal-ai environment. https:\/\/ceur-ws. org\/Vol-3169\/paper2. pdf (2022)."},{"key":"e_1_3_3_2_59_1","unstructured":"Guanzhi Wang Yuqi Xie Yunfan Jiang Ajay Mandlekar Chaowei Xiao Yuke Zhu Linxi\u00a0(Jim) Fan and Anima Anandkumar. 2023c. Voyager: An Open-Ended Embodied Agent with Large Language Models. Trans. Mach. Learn. Res. 2024 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258887849"},{"key":"e_1_3_3_2_60_1","unstructured":"Xuezhi Wang Jason Wei Dale Schuurmans Quoc Le Ed Chi Sharan Narang Aakanksha Chowdhery and Denny Zhou. 2023b. Self-Consistency Improves Chain of Thought Reasoning in Language Models. arxiv:https:\/\/arXiv.org\/abs\/2203.11171\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2203.11171"},{"key":"e_1_3_3_2_61_1","unstructured":"Yi\u00a0Ru Wang Jiafei Duan Dieter Fox and Siddhartha Srinivasa. 2023a. NEWTON: Are Large Language Models Capable of Physical Reasoning? arxiv:https:\/\/arXiv.org\/abs\/2310.07018\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2310.07018"},{"key":"e_1_3_3_2_62_1","unstructured":"Nicholas Watters Daniel Zoran Theophane Weber Peter Battaglia Razvan Pascanu and Andrea Tacchetti. 2017. Visual interaction networks: Learning a physics simulator from video. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_2_63_1","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Brian Ichter Fei Xia Ed Chi Quoc Le and Denny Zhou. 2023. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2201.11903\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2201.11903"},{"key":"e_1_3_3_2_64_1","doi-asserted-by":"crossref","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Fei Xia Ed Chi Quoc\u00a0V Le Denny Zhou et\u00a0al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022) 24824\u201324837.","DOI":"10.52202\/068431-1800"},{"key":"e_1_3_3_2_65_1","doi-asserted-by":"crossref","unstructured":"Juri Yanase and Evangelos Triantaphyllou. 2019. A systematic survey of computer-aided diagnosis in medicine: Past and present developments. Expert Syst. Appl. 138 (2019). https:\/\/api.semanticscholar.org\/CorpusID:199019309","DOI":"10.1016\/j.eswa.2019.112821"},{"key":"e_1_3_3_2_66_1","doi-asserted-by":"crossref","unstructured":"Will Yeadon Alex Peach and Craig Testrow. 2024. A comparison of human GPT-3.5 and GPT-4 performance in a university-level coding course. Scientific Reports 14 1 (Oct. 2024). https:\/\/doi.org\/10.1038\/s41598-024-73634-y","DOI":"10.1038\/s41598-024-73634-y"},{"key":"e_1_3_3_2_67_1","unstructured":"Haiyan Zhao Hanjie Chen Fan Yang Ninghao Liu Huiqi Deng Hengyi Cai Shuaiqiang Wang Dawei Yin and Mengnan Du. 2023. Explainability for Large Language Models: A Survey. arxiv:https:\/\/arXiv.org\/abs\/2309.01029\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2309.01029"}],"event":{"name":"SIGGRAPH Conference Papers '25: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Vancouver BC Canada","acronym":"SIGGRAPH Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721238.3730742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:00:56Z","timestamp":1774018856000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721238.3730742"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":66,"alternative-id":["10.1145\/3721238.3730742","10.1145\/3721238"],"URL":"https:\/\/doi.org\/10.1145\/3721238.3730742","relation":{},"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}