# Intersymbolic AI: Interlinking Symbolic AI and Subsymbolic AI

arXiv: https://arxiv.org/abs/2406.11563 · HTML: https://mlsanity.com/paper/2406.11563/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 112 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://mlsanity.com/paper/1712.01815/) (2017)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Predictability and Surprise in Large Generative Models](https://mlsanity.com/paper/2202.07785/) (2022)
- [Thinking Fast and Slow in AI](https://mlsanity.com/paper/2010.06002/) (2020)
- [Graph Representations for Higher-Order Logic and Theorem Proving](https://mlsanity.com/paper/1905.10006/) (2019)
- [A formal proof of the Kepler conjecture](https://mlsanity.com/paper/1501.02155/) (2015)
- [Turning 30: New Ideas in Inductive Logic Programming](https://mlsanity.com/paper/2002.11002/) (2020)
- [Verifiably Safe Off-Model Reinforcement Learning](https://mlsanity.com/paper/1902.05632/) (2019)
- [Probabilistic Model Checking and Autonomy](https://mlsanity.com/paper/2111.10630/) (2021)
- [Provably Safe Neural Network Controllers via Differential Dynamic Logic](https://mlsanity.com/paper/2402.10998/) (2024)
- [When to Trust AI: Advances and Challenges for Certification of Neural Networks](https://mlsanity.com/paper/2309.11196/) (2023)
- [Learning to Find Proofs and Theorems by Learning to Refine Search Strategies: The Case of Loop Invariant Synthesis](https://mlsanity.com/paper/2205.14229/) (2022)
- [CESAR: Control Envelope Synthesis via Angelic Refinements](https://mlsanity.com/paper/2311.02833/) (2023)
- [Differential Game Logic](https://mlsanity.com/paper/1408.1980/) (2014)
- [Differential Equation Invariance Axiomatization](https://mlsanity.com/paper/1905.13429/) (2019)
- [Pegasus: Sound Continuous Invariant Generation](https://mlsanity.com/paper/2005.09348/) (2020)
- [Automating Resolution is NP-Hard](https://mlsanity.com/paper/1904.02991/) (2019)
- [Scalable SAT Solving in the Cloud](https://mlsanity.com/paper/2205.06590/) (2022)

## Built on by (most cited first, 3 of 3)

- [Next Steps in LLM-Supported Java Verification](https://mlsanity.com/paper/2502.01573/) (2025)
- [Towards Responsible and Trustworthy Educational Data Mining: Comparing Symbolic, Sub-Symbolic, and Neural-Symbolic AI Methods](https://mlsanity.com/paper/2504.00615/) (2025)
- [Protected Cores Are Not Enough: Certifying AI-Proposed Revisions of Temporal Specifications](https://mlsanity.com/paper/2609.33461/) (2026)

## Abstract (arXiv)

This perspective piece calls for the study of the new field of Intersymbolic AI, by which we mean the combination of symbolic AI, whose building blocks have inherent significance/meaning, with subsymbolic AI, whose entirety creates significance/effect despite the fact that individual building blocks escape meaning. Canonical kinds of symbolic AI are logic, games and planning. Canonical kinds of subsymbolic AI are (un)supervised machine and reinforcement learning. Intersymbolic AI interlinks the worlds of symbolic AI with its compositional symbolic significance and meaning and of subsymbolic AI with its summative significance or effect to enable culminations of insights from both worlds by going between and across symbolic AI insights with subsymbolic AI techniques that are being helped by symbolic AI principles. For example, Intersymbolic AI may start with symbolic AI to understand a dynamic system, continue with subsymbolic AI to learn its control, and end with symbolic AI to safely use the outcome of the learned subsymbolic AI controller in the dynamic system. The way Intersymbolic AI combines both symbolic and subsymbolic AI to increase the effectiveness of AI compared to either kind of AI alone is likened to the way that the combination of both conscious and subconscious thought increases the effectiveness of human thought compared to either kind of thought alone. Some successful contributions to the Intersymbolic AI paradigm are surveyed here but many more are considered possible by advancing Intersymbolic AI.