Neuro-symbolic AI

Neuro-symbolic AI is a subfield of artificial intelligence that combines neural networks and symbolic AI approaches, such as knowledge representation and automated reasoning, to create more robust, more reliable, and more trustworthy AI. This combination allows statistical patterns to be combined with explicitly defined rules and knowledge to give AI systems the ability to better represent, reason and generalize. Thus, neuro-symbolic AI provides a reasoning infrastructure to state-of-the-art machine learning for solving a wider range of problems more effectively.

Neuro-symbolic AI recognises the value of deep learning as the “substrate” of AI that provides efficient computational models of learning from data. At the same time, it seeks to address deep learning’s main limitations: lack of reliability, data and energy efficiency, fairness, and trust. Thus, neuro-symbolic AI is argued to leverage the strengths of the two predominant approaches to AI, at the same time mitigating their weaknesses. Many leading computer scientists support this view. For example, Leslie Valiant believes that neuro-symbolic AI will be able to "reconcile the statistical nature of learning and the logical nature of reasoning," while Sepp Hochreiter claims that "the most promising approach to a broad AI is a neuro-symbolic AI, that is, a bilateral AI that combines methods from symbolic and sub-symbolic AI."

In recent years, neuro-symbolic AI has been called the third wave of AI, where the first wave (1980s–2000s) was the era of logic-based symbolic AI, and the second wave (2015–present) relied on connectionist AI, that is, neural networks and deep learning. Neuro-symbolic AI gained wider industrial adoption and public visibility in 2025 to address hallucination in large language models (LLMs); for example, Amazon applied it in its Vulcan warehouse robots and Rufus AI shopping assistant to enhance accuracy and decision-making.

To date, no single predominant approach exists for how to achieve neuro-symbolic AI. Research in the field is focused on what makes the best way to assemble the two main AI paradigms into one architecture, the neuro-symbolic methodology to do so, appropriate metrics such as "accuracy divided by compute" to account for data efficiency requirements and knowledge reuse, the representation capacity of neural models of computation, the principled combination of learning and reasoning using the interplay of continuous and discrete processes, and applications of neuro-symbolic AI in domain-specific fields. Overall, however, neuro-symbolic AI systems can be divided into two main categories:

  • hybrid systems with a neural and a symbolic component (e.g., LLMs and Theorem Provers as in AlphaProof Nexus system by Google DeepMind, which was able to prove several open Erdős problems), and
  • neuro-symbolic systems integrating learning and reasoning within a neural network, so that, informed by the theory of learning and formal reasoning under uncertainty, these systems are normally based on fuzzy and non-classical logics or probabilistic methods made differentiable for use within neural networks.