Building Intelligent Agents with Neuro-Symbolic Concepts
Author(s)
Mao, Jiayuan
Tenenbaum, Joshua
Wu, Jiajun
Date Issued
January 28, 2026
Journal
Communications of the ACM
Publisher
ACM|Communications of the ACM
Citation
Jiayuan Mao, Joshua B. Tenenbaum, and Jiajun Wu. 2026. Building Intelligent Agents with Neuro-Symbolic Concepts. Commun. ACM 69, 2 (February 2026), 69–79.
Version
Final published version
Abstract
This article presents a concept-centric paradigm for building agents that can learn continually and reason flexibly. The concept-centric agent utilizes a vocabulary of neuro-symbolic concepts. These concepts, such as object, relation, and action concepts, are grounded on 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 representations. Leveraging such neuro-symbolic concepts, the agent can efficiently learn and recombine them 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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
http://dx.doi.org/10.1145/3715316
