Journal article · 2026 · Open access
Building Intelligent Agents with Neuro-Symbolic Concepts
Communications of the ACM, 69(2), 69–79 · Published 28 January 2026 · DOI 10.1145/3715316
In brief
“Building Intelligent Agents with Neuro-Symbolic Concepts” is a 2026 journal article by Jiayuan Mao and 2 co-authors, published in Communications of the ACM. OpenAlex counts 16 citations as of 17 November 2026, which puts it in the top 5% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Communications of the ACM.
- Citations
- 16
- Most cited in
- 2026 (13)
- Field-weighted impact
- 14.02
- References
- 33
- Authors
- 3
Abstract
We present a concept-centric paradigm for building agents that can learn continually and reason flexibly. The agent utilizes a vocabulary of neuro-symbolic concepts . 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.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Mao, J., Tenenbaum, J. B., & Wu, J. (2026). Building Intelligent Agents with Neuro-Symbolic Concepts. Communications of the ACM, 69(2), 69–79. https://doi.org/10.1145/3715316
MLA 9
Mao, Jiayuan, et al. “Building Intelligent Agents with Neuro-Symbolic Concepts.” Communications of the ACM, vol. 69, no. 2, 2026, pp. 69–79. https://doi.org/10.1145/3715316.
Chicago
Mao, Jiayuan, Joshua B. Tenenbaum, and Jiajun Wu. 2026. “Building Intelligent Agents with Neuro-Symbolic Concepts.” Communications of the ACM 69 (2): 69–79. https://doi.org/10.1145/3715316.
Harvard
Mao, J., Tenenbaum, J. B. and Wu, J. (2026) ‘Building Intelligent Agents with Neuro-Symbolic Concepts’, Communications of the ACM, 69(2), pp. 69–79. doi:10.1145/3715316.
IEEE
J. Mao, J. B. Tenenbaum, and J. Wu, “Building Intelligent Agents with Neuro-Symbolic Concepts,” Communications of the ACM, vol. 69, no. 2, pp. 69–79, 2026, doi: 10.1145/3715316.
BibTeX
@article{mao2026building,
title = {{Building Intelligent Agents with Neuro-Symbolic Concepts}},
author = {Mao, Jiayuan and Tenenbaum, Joshua B. and Wu, Jiajun},
journal = {Communications of the ACM},
year = {2026},
volume = {69},
number = {2},
pages = {69--79},
doi = {10.1145/3715316},
url = {https://doi.org/10.1145/3715316}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- neuro-symbolic AI
- intelligent agents
- continual learning
- compositional generalization
- zero-shot transfer
- neural embeddings
- robotic manipulation
- 3D scene understanding
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Mao, J., Tenenbaum, J. B., & Wu, J. (2026). Building Intelligent Agents with Neuro-Symbolic Concepts. Communications of the ACM, 69(2), 69–79. https://doi.org/10.1145/3715316
How many times has this paper been cited?
16 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Communications of the ACM: sign in and open the full text from this page.
Who wrote this paper?
Jiayuan Mao, Joshua B. Tenenbaum, Jiajun Wu.
What is the DOI of this paper?
10.1145/3715316, permanently at https://doi.org/10.1145/3715316. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.