{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:06:02Z","timestamp":1776679562616,"version":"3.51.2"},"publisher-location":"Singapore","reference-count":62,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819570775","type":"print"},{"value":"9789819570782","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-7078-2_18","type":"book-chapter","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T09:22:15Z","timestamp":1776676935000},"page":"272-287","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Little Less Conversation, a\u00a0Little More Action, Please: Investigating the\u00a0Physical Common-Sense of\u00a0LLMs in\u00a0a\u00a03D Embodied Environment"],"prefix":"10.1007","author":[{"given":"Matteo G.","family":"Mecattaf","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ben","family":"Slater","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marko","family":"Te\u0161i\u0107","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Prunty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantinos","family":"Voudouris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lucy G.","family":"Cheke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"18_CR1","unstructured":"Ahn, M., et al.: Do as i can, not as i say: grounding language in robotic affordances. arXiv preprint arXiv:2204.01691 (2022)"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Aroca-Ouellette, S., Paik, C., Roncone, A., Kann, K.: Prost: physical reasoning of objects through space and time. arXiv preprint arXiv:2106.03634 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.404"},{"issue":"7","key":"18_CR3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1007210","volume":"15","author":"CJ Bates","year":"2019","unstructured":"Bates, C.J., Yildirim, I., Tenenbaum, J.B., Battaglia, P.: Modeling human intuitions about liquid flow with particle-based simulation. PLoS Comput. Biol. 15(7), e1007210 (2019)","journal-title":"PLoS Comput. Biol."},{"key":"18_CR4","unstructured":"Battaglia, P., et al.: Computational models of intuitive physics. In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol.\u00a034 (2012)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Bender, E.M., Koller, A.: Climbing towards NLU: on meaning, form, and understanding in the age of data. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 5185\u20135198 (2020)","DOI":"10.18653\/v1\/2020.acl-main.463"},{"key":"18_CR6","unstructured":"Beyret, B., Hern\u00e1ndez-Orallo, J., Cheke, L., Halina, M., Shanahan, M., Crosby, M.: The Animal-AI environment: Training and testing animal-like artificial cognition. arXiv preprint arXiv:1909.07483 (2019)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Bisk, Y., Zellers, R., Gao, J., Choi, Y., et\u00a0al.: PIQA: reasoning about physical commonsense in natural language. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 7432\u20137439 (2020)","DOI":"10.1609\/aaai.v34i05.6239"},{"issue":"4","key":"18_CR8","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.1037\/0033-295X.111.4.1061","volume":"111","author":"D Borsboom","year":"2004","unstructured":"Borsboom, D., Mellenbergh, G.J., Van Heerden, J.: The concept of validity. Psychol. Rev. 111(4), 1061 (2004)","journal-title":"Psychol. Rev."},{"key":"18_CR9","unstructured":"Burden, J.: Evaluating AI evaluation: perils and prospects. arXiv preprint arXiv:2407.09221 (2024)"},{"key":"18_CR10","unstructured":"Burden, J., Voudouris, K., Burnell, R., Rutar, D., Cheke, L., Hern\u00e1ndez-Orallo, J.: Inferring capabilities from task performance with Bayesian triangulation. arXiv preprint arXiv:2309.11975 (2023)"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Burnell, R., Burden, J., Rutar, D., Voudouris, K., Cheke, L., Hern\u00e1ndez-Orallo, J.: Not a number: identifying instance features for capability-oriented evaluation. In: IJCAI, pp. 2827\u20132835 (2022)","DOI":"10.24963\/ijcai.2022\/392"},{"key":"18_CR12","unstructured":"Buschoff, L.M.S., Akata, E., Bethge, M., Schulz, E.: Have we built machines that think like people? arXiv preprint arXiv:2311.16093 (2024)"},{"issue":"1718","key":"18_CR13","first-page":"2621","volume":"278","author":"C Chiandetti","year":"2011","unstructured":"Chiandetti, C., Vallortigara, G.: Intuitive physical reasoning about occluded objects by inexperienced chicks. Proc. Roy. Soc. B Biol. Sci. 278(1718), 2621\u20132627 (2011)","journal-title":"Proc. Roy. Soc. B Biol. Sci."},{"issue":"4","key":"18_CR14","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1037\/h0040957","volume":"52","author":"LJ Cronbach","year":"1955","unstructured":"Cronbach, L.J., Meehl, P.E.: Construct validity in psychological tests. Psychol. Bull. 52(4), 281 (1955)","journal-title":"Psychol. Bull."},{"issue":"5","key":"18_CR15","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1038\/s42256-019-0050-3","volume":"1","author":"M Crosby","year":"2019","unstructured":"Crosby, M., Beyret, B., Halina, M.: The animal-AI Olympics. Nat. Mach. Intell. 1(5), 257 (2019)","journal-title":"Nat. Mach. Intell."},{"key":"18_CR16","unstructured":"Crosby, M., Beyret, B., Shanahan, M., Hern\u00e1ndez-Orallo, J., Cheke, L., Halina, M.: The animal-AI testbed and competition. In: Neurips 2019 Competition and Demonstration Track, pp. 164\u2013176. PMLR (2020)"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Dagan, G., Keller, F., Lascarides, A.: Learning the effects of physical actions in a multi-modal environment. arXiv preprint arXiv:2301.11845 (2023)","DOI":"10.18653\/v1\/2023.findings-eacl.10"},{"key":"18_CR18","unstructured":"Driess, D., et al.: Palm-e: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"key":"18_CR19","unstructured":"Du, Y., et al.: Guiding pretraining in reinforcement learning with large language models. In: International Conference on Machine Learning, pp. 8657\u20138677. PMLR (2023)"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Goddu, M.K., Gopnik, A.: The development of human causal learning and reasoning. Nat. Rev. Psychol. 1\u201321 (2024)","DOI":"10.1038\/s44159-024-00300-5"},{"issue":"8","key":"18_CR21","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1016\/j.tics.2004.06.005","volume":"8","author":"A Gopnik","year":"2004","unstructured":"Gopnik, A., Schulz, L.: Mechanisms of theory formation in young children. Trends Cogn. Sci. 8(8), 371\u2013377 (2004)","journal-title":"Trends Cogn. Sci."},{"key":"18_CR22","unstructured":"Hafner, D.: Benchmarking the spectrum of agent capabilities. arXiv preprint arXiv:2109.06780 (2021)"},{"key":"18_CR23","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1007\/s10462-016-9505-7","volume":"48","author":"J Hern\u00e1ndez-Orallo","year":"2017","unstructured":"Hern\u00e1ndez-Orallo, J.: Evaluation in artificial intelligence: from task-oriented to ability-oriented measurement. Artif. Intell. Rev. 48, 397\u2013447 (2017)","journal-title":"Artif. Intell. Rev."},{"key":"18_CR24","unstructured":"Hu, S., et al.: A survey on large language model-based game agents. arXiv preprint arXiv:2404.02039 (2024)"},{"key":"18_CR25","unstructured":"Jassim, S., Holubar, M., Richter, A., Wolff, C., Ohmer, X., Bruni, E.: Grasp: a novel benchmark for evaluating language grounding and situated physics understanding in multimodal language models. arXiv preprint arXiv:2311.09048 (2024)"},{"key":"18_CR26","unstructured":"Jiang, Y., et al.: VIMA: general robot manipulation with multimodal prompts. arXiv preprint arXiv:2210.03094, vol. 2, no. 3, p. 6 (2022)"},{"key":"18_CR27","unstructured":"Juliani, A.: Unity: a general platform for intelligent agents. arXiv preprint arXiv:1809.02627 (2018)"},{"issue":"10","key":"18_CR28","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1016\/j.tics.2017.06.002","volume":"21","author":"JR Kubricht","year":"2017","unstructured":"Kubricht, J.R., Holyoak, K.J., Lu, H.: Intuitive physics: current research and controversies. Trends Cogn. Sci. 21(10), 749\u2013759 (2017)","journal-title":"Trends Cogn. Sci."},{"key":"18_CR29","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837","volume":"40","author":"BM Lake","year":"2017","unstructured":"Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. Behav. Brain Sci. 40, e253 (2017)","journal-title":"Behav. Brain Sci."},{"key":"18_CR30","unstructured":"Lakoff, G., Johnson, M.: Metaphors We Live By. University of Chicago Press (2008)"},{"key":"18_CR31","unstructured":"Liu, J., et al.: LLM-powered hierarchical language agent for real-time human-AI coordination. arXiv preprint arXiv:2312.15224 (2023)"},{"key":"18_CR32","unstructured":"Ma, W., et al.: Large language models play starcraft ii: benchmarks and a chain of summarization approach. arXiv preprint arXiv:2312.11865 (2023)"},{"key":"18_CR33","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/j.neunet.2022.03.037","volume":"152","author":"Y Matsuo","year":"2022","unstructured":"Matsuo, Y., et al.: Deep learning, reinforcement learning, and world models. Neural Netw. 152, 267\u2013275 (2022)","journal-title":"Neural Netw."},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Mitchell, M.: Why AI is harder than we think. arXiv preprint arXiv:2104.12871 (2021)","DOI":"10.1145\/3449639.3465421"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Povinelli, D.J.: Folk Physics for Apes: The Chimpanzee\u2019s Theory of How the World Works. Oxford University Press (2003)","DOI":"10.1093\/acprof:oso\/9780198572190.001.0001"},{"key":"18_CR36","unstructured":"Prunty, J., O\u2019Flynn, A., Quinn, P., Cheke, L.G.: Intuit: investigating intuitive reasoning in humans and language models. In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol.\u00a047 (2025)"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Puig, X., et al.: Virtualhome: simulating household activities via programs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8494\u20138502 (2018)","DOI":"10.1109\/CVPR.2018.00886"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Ranasinghe, K., Shukla, S.N., Poursaeed, O., Ryoo, M.S., Lin, T.Y.: Learning to localize objects improves spatial reasoning in visual-LLMs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12977\u201312987 (2024)","DOI":"10.1109\/CVPR52733.2024.01233"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Rutar, D., Cheke, L.G., Hern\u00e1ndez-Orallo, J., Markelius, A., Schellaert, W.: General interaction battery: simple object navigation and affordances (gibsona). Available at SSRN 4924246 (2024)","DOI":"10.2139\/ssrn.4871025"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Sap, M., Shwartz, V., Bosselut, A., Choi, Y., Roth, D.: Commonsense reasoning for natural language processing. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts, pp. 27\u201333 (2020)","DOI":"10.18653\/v1\/2020.acl-tutorials.7"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Shanahan, M.: Embodiment and the Inner Life: Cognition and Consciousness in the Space of Possible Minds. Oxford University Press (2010)","DOI":"10.1093\/acprof:oso\/9780199226559.001.0001"},{"issue":"11","key":"18_CR42","doi-asserted-by":"publisher","first-page":"862","DOI":"10.1016\/j.tics.2020.09.002","volume":"24","author":"M Shanahan","year":"2020","unstructured":"Shanahan, M., Crosby, M., Beyret, B., Cheke, L.: Artificial intelligence and the common sense of animals. Trends Cogn. Sci. 24(11), 862\u2013872 (2020)","journal-title":"Trends Cogn. Sci."},{"key":"18_CR43","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/s42113-018-0007-3","volume":"1","author":"KA Smith","year":"2018","unstructured":"Smith, K.A., Battaglia, P.W., Vul, E.: Different physical intuitions exist between tasks, not domains. Comput. Brain Behav. 1, 101\u2013118 (2018)","journal-title":"Comput. Brain Behav."},{"key":"18_CR44","unstructured":"Storks, S., Gao, Q., Chai, J.Y.: Commonsense reasoning for natural language understanding: a survey of benchmarks, resources, and approaches. arXiv preprint arXiv:1904.01172, pp. 1\u201360 (2019)"},{"key":"18_CR45","unstructured":"Sumers, T.R., Yao, S., Narasimhan, K., Griffiths, T.L.: Cognitive architectures for language agents. arXiv preprint arXiv:2309.02427 (2023)"},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Tenenbaum, J.B., Kemp, C., Griffiths, T.L., Goodman, N.D.: How to grow a mind: statistics, structure, and abstraction. Science 331(6022), 1279\u20131285 (2011)","DOI":"10.1126\/science.1192788"},{"issue":"1","key":"18_CR47","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1207\/S15327078IN0101_02","volume":"1","author":"E Thelen","year":"2000","unstructured":"Thelen, E.: Grounded in the world: developmental origins of the embodied mind. Infancy 1(1), 3\u201328 (2000)","journal-title":"Infancy"},{"key":"18_CR48","unstructured":"Tian, Y., et al.: Macgyver: are large language models creative problem solvers? arXiv preprint arXiv:2311.09682 (2023)"},{"key":"18_CR49","unstructured":"Trott, A., Xiong, C., Socher, R.: Interpretable counting for visual question answering. arXiv preprint arXiv:1712.08697 (2017)"},{"key":"18_CR50","unstructured":"Voudouris, K., et al.: Animal-AI 3: what\u2019s new & why you should care. arXiv preprint arXiv:2312.11414 (2023)"},{"key":"18_CR51","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2022.711821","volume":"13","author":"K Voudouris","year":"2022","unstructured":"Voudouris, K., et al.: Direct human-AI comparison in the animal-AI environment. Front. Psychol. 13, 711821 (2022)","journal-title":"Front. Psychol."},{"key":"18_CR52","unstructured":"Voudouris, K., et al.: Evaluating object permanence in embodied agents using the animal-AI environment. In: EBeM\u201922: Workshop on AI Evaluation Beyond Metrics, Vienna, Austria (2022)"},{"key":"18_CR53","unstructured":"Voudouris, K., Liu, J.D., Siwinska, N., Schellaert, W., Cheke, L.G.: Investigating object permanence in deep reinforcement learning agents. In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol.\u00a046 (2024)"},{"key":"18_CR54","doi-asserted-by":"crossref","unstructured":"Voudouris, K., et al.: The animal-AI environment: a virtual laboratory for comparative cognition and artificial intelligence research. Behav. Res. Methods 57 (2025)","DOI":"10.3758\/s13428-025-02616-3"},{"key":"18_CR55","unstructured":"Wang, G., et al.: Voyager: an open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291 (2023)"},{"issue":"6","key":"18_CR56","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1","volume":"18","author":"L Wang","year":"2024","unstructured":"Wang, L., et al.: A survey on large language model based autonomous agents. Front. Comput. Sci. 18(6), 186345 (2024)","journal-title":"Front. Comput. Sci."},{"key":"18_CR57","doi-asserted-by":"crossref","unstructured":"Wang, Y.R., Duan, J., Fox, D., Srinivasa, S.: Newton: are large language models capable of physical reasoning? arXiv preprint arXiv:2310.07018 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.652"},{"issue":"1","key":"18_CR58","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1037\/0096-3445.136.1.82","volume":"136","author":"P Wolff","year":"2007","unstructured":"Wolff, P.: Representing causation. J. Exp. Psychol. Gen. 136(1), 82 (2007)","journal-title":"J. Exp. Psychol. Gen."},{"key":"18_CR59","unstructured":"Xiang, J., et al.: Language models meet world models: embodied experiences enhance language models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"18_CR60","unstructured":"Xu, C., Guan, S., Greene, D., Kechadi, M., et\u00a0al.: Benchmark data contamination of large language models: a survey. arXiv preprint arXiv:2406.04244 (2024)"},{"key":"18_CR61","unstructured":"Yao, S., et al.: React: synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629 (2022)"},{"key":"18_CR62","doi-asserted-by":"crossref","unstructured":"Zellers, R., et al.: Piglet: language grounding through neuro-symbolic interaction in a 3D world. arXiv preprint arXiv:2106.00188 (2021)","DOI":"10.18653\/v1\/2021.acl-long.159"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2025: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-7078-2_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T09:23:09Z","timestamp":1776676989000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7078-2_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819570775","9789819570782"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7078-2_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"21 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}