{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T08:03:25Z","timestamp":1769760205451,"version":"3.49.0"},"reference-count":40,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T00:00:00Z","timestamp":1769644800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Commun. ACM"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:p>\n                    We present a concept-centric paradigm for building agents that can learn continually and reason flexibly. The agent utilizes a vocabulary of\n                    <jats:italic toggle=\"yes\">neuro-symbolic concepts<\/jats:italic>\n                    . These concepts of objects, relations, and actions are grounded in sensory inputs and actuation outputs; they are also compositional, allowing for the creation of novel concepts through their structural combination. To facilitate learning and reasoning, the concepts are typed and represented using a combination of symbolic programs and neural network embeddings. Leveraging the complementary features of neural and symbolic representations, an agent can efficiently learn and recombine concepts to solve various tasks across different domains, ranging from 2D images, videos, 3D scenes, and robotic manipulation tasks. This concept-centric framework offers several advantages, including data efficiency, compositional generalization, continual learning, and zero-shot transfer.\n                  <\/jats:p>","DOI":"10.1145\/3715316","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T16:38:06Z","timestamp":1769618286000},"page":"69-79","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Building Intelligent Agents with Neuro-Symbolic Concepts"],"prefix":"10.1145","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4798-3748","authenticated-orcid":false,"given":"Jiayuan","family":"Mao","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, Cambridge, Massachusetts, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1925-2035","authenticated-orcid":false,"given":"Joshua B.","family":"Tenenbaum","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Department of Brain and Cognitive Sciences, Cambridge, Massachusetts, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4176-343X","authenticated-orcid":false,"given":"Jiajun","family":"Wu","sequence":"additional","affiliation":[{"name":"Stanford University, Computer Science, Stanford, California, United States"}]}],"member":"320","published-online":{"date-parts":[[2026,1,29]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2017.02.009"},{"key":"e_1_3_1_3_2","unstructured":"Amizadeh S. et al. Neuro-symbolic visual reasoning: Disentangling \u2018visual\u2019 from \u2018reasoning.\u2019\u00a0In Intern. Conf. on Machine Learning\u00a0(2020)."},{"key":"e_1_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Andreas J. Rohrbach M. Darrell T. and Klein D. Neural module networks. In IEEE\/CVF Conf. on Computer Vision and Pattern Recognition\u00a0(2016).","DOI":"10.1109\/CVPR.2016.12"},{"key":"e_1_3_1_5_2","unstructured":"Barbiero P. et al. Interpretable neural-symbolic concept reasoning. In Intern. Conf. on Machine Learning\u00a0(2023)."},{"key":"e_1_3_1_6_2","unstructured":"Chen Z. et al. Grounding physical concepts of objects and events through dynamic visual reasoning. In Intern. Conf. on Learning Representations\u00a0(2021)."},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.00122"},{"key":"e_1_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Demeester T. Rockt\u00e4schel T. and Riedel S. Lifted rule injection for relation embeddings. In Conf. on Empirical Methods in Natural Language Processing\u00a0(2016).","DOI":"10.18653\/v1\/D16-1146"},{"key":"e_1_3_1_9_2","unstructured":"D\u00eddac S. Menon S. and Vondrick C. ViperGPT: Visual Inference via Python execution for reasoning. In IEEE\/CVF Intern. Conf. on Computer Vision\u00a0(2023)."},{"key":"e_1_3_1_10_2","unstructured":"Ding M. et al. Dynamic visual reasoning by learning differentiable physics models from video and language. In Advances in Neural Information Processing Systems\u00a0(2021)."},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2022.0050"},{"key":"e_1_3_1_12_2","unstructured":"Endo M. Hsu J. Li J. and Wu J. Motion question answering via modular motion programs. In Intern. Conf. on Machine Learning\u00a0(2023)."},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1551-6709.2010.01104.x"},{"key":"e_1_3_1_14_2","unstructured":"Friedman N. Getoor L. Koller D. and Pfeffer A. Learning probabilistic relational models. In Intern. Joint Conf. on Artificial Intelligence\u00a0(1999)."},{"key":"e_1_3_1_15_2","unstructured":"Han C. et al. Visual concept metaconcept learning. In Advances in Neural Information Processing Systems (2019)."},{"key":"e_1_3_1_16_2","unstructured":"Hsu J. et al. What makes a maze look like a maze?\u00a0In Intern. Conf. on Learning Representations\u00a0(2025)."},{"key":"e_1_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Hsu J. Mao J. and Wu J. NS3D: Neuro-symbolic grounding of 3D objects and relations. In IEEE\/CVF Conf. on Computer Vision and Pattern Recognition\u00a0(2023).","DOI":"10.1109\/CVPR52729.2023.00257"},{"key":"e_1_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Johnson J. et al. CLEVR: A diagnostic dataset for compositional language and elementary visual reasoning. In IEEE\/CVF Conf. on Computer Vision and Pattern Recognition (2017).","DOI":"10.1109\/CVPR.2017.215"},{"key":"e_1_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Kalithasan N. et al. Learning neuro-symbolic programs for language guided robot manipulation. In IEEE Intern. Conf. on Robotics and Automation\u00a0(2023).","DOI":"10.1109\/ICRA48891.2023.10160545"},{"key":"e_1_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Li Q. Huang S. Hong Y. and Zhu S.C.\u00a0A competence-aware curriculum for visual concepts learning via question answering. In European Conf. on Computer Vision\u00a0(2020).","DOI":"10.1007\/978-3-030-58536-5_9"},{"key":"e_1_3_1_21_2","unstructured":"Manhaeve R. et al. Deepproblog: Neural probabilistic logic programming. In Advances in Neural Information Processing Systems\u00a0(2018)."},{"key":"e_1_3_1_22_2","unstructured":"Mao J. et al. The Neuro-symbolic concept learner: Interpreting scenes words and sentences from natural supervision. In Intern. Conf. on Learning Representations\u00a0(2019)."},{"key":"e_1_3_1_23_2","unstructured":"Mao J. Lozano-P\u00e9rez T. Tenenbaum J.B. and Kaelbling L. PDSketch: Integrated domain programming learning and planning. In Advances in Neural Information Processing Systems\u00a0(2022)."},{"key":"e_1_3_1_24_2","unstructured":"Mao J. et al. Grammar-based grounded language learning. In Advances in Neural Information Processing Systems\u00a0(2021)."},{"key":"e_1_3_1_25_2","volume-title":"Concepts: Core Readings.","author":"Margolis E.","year":"1999","unstructured":"Margolis, E. and Laurence, S. Concepts: Core Readings.\u00a0The MIT Press\u00a0(1999)."},{"key":"e_1_3_1_26_2","unstructured":"Mei L. et al. FALCON: Fast visual concept learning by integrating images linguistic descriptions and conceptual relations. In Intern. Conf. on Learning Representations\u00a0(2022)."},{"key":"e_1_3_1_27_2","volume-title":"Frames of Mind: Constraints on the Common-Sense Conception of the Mental.","author":"Morton A.","year":"1980","unstructured":"Morton, A. Frames of Mind: Constraints on the Common-Sense Conception of the Mental.\u00a0Oxford University Press (1980)."},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/0743-1066(94)90035-3"},{"key":"e_1_3_1_29_2","unstructured":"Petersen F. Borgelt C. Kuehne H. and Deussen O. Learning with algorithmic supervision via continuous relaxations. In Advances in Neural Information Processing Systems\u00a0(2021)."},{"key":"e_1_3_1_30_2","unstructured":"Prabhudesai M. et al. Disentangling 3D prototypical networks for few-shot concept learning. In Intern. Conf. on Learning Representations\u00a0(2021)."},{"key":"e_1_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Rockt\u00e4schel T. Singh S. and Riedel S. Injecting logical background knowledge into embeddings for relation extraction. In Annual Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2015).","DOI":"10.3115\/v1\/N15-1118"},{"key":"e_1_3_1_32_2","first-page":"1","article-title":"Neuro-symbolic predicate invention: Learning relational concepts from visual scenes","author":"Sha J.","year":"2024","unstructured":"Sha, J., Shindo, H., Kersting, K., and Dhami, D.S. Neuro-symbolic predicate invention: Learning relational concepts from visual scenes. Neurosymbolic Artificial Intelligence\u00a0(2024), 1\u201326.","journal-title":"Neurosymbolic Artificial Intelligence"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06320-1"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-024-06610-2"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.15027"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00568-3"},{"key":"e_1_3_1_37_2","unstructured":"Wang P.W. Donti P. Wilder B. and Kolter Z. SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver. In Intern. Conf. on Machine Learning\u00a0(2019)."},{"key":"e_1_3_1_38_2","unstructured":"Wang R. et al. Programmatically grounded compositionally generalizable robotic manipulation. In Intern. Conf. on Learning Representations\u00a0(2023)."},{"key":"e_1_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Wu H. et al. Unified visual-semantic embeddings: Bridging vision and language with structured meaning representations. In IEEE\/CVF Conf. on Computer Vision and Pattern Recognition\u00a0(2019).","DOI":"10.1109\/CVPR.2019.00677"},{"key":"e_1_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Yang W.C. Marra G. Rens G. and Raedt L.D. Safe reinforcement learning via probabilistic logic shields. In Intern. Joint Conf. on Artificial Intelligence\u00a0(2023).","DOI":"10.24963\/ijcai.2023\/637"},{"key":"e_1_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Yang Z. Ishay A. and Lee J. NeurASP: Embracing neural networks into answer set programming. In Intern. Joint Conf. on Artificial Intelligence\u00a0(2020).","DOI":"10.24963\/ijcai.2020\/243"}],"container-title":["Communications of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/full\/10.1145\/3715316","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3715316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T17:05:19Z","timestamp":1769706319000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715316"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,29]]},"references-count":40,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1145\/3715316"],"URL":"https:\/\/doi.org\/10.1145\/3715316","relation":{},"ISSN":["0001-0782","1557-7317"],"issn-type":[{"value":"0001-0782","type":"print"},{"value":"1557-7317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,29]]},"assertion":[{"value":"2024-06-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}