# Symbolic Behaviour in Artificial Intelligence

arXiv: https://arxiv.org/abs/2102.03406 · HTML: https://mlsanity.com/paper/2102.03406/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 145 references that are in the map.
- First posted on arXiv 5 Feb 2021.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [Measuring Catastrophic Forgetting in Neural Networks](https://mlsanity.com/paper/1708.02072/) (2017)
- [Analysing Mathematical Reasoning Abilities of Neural Models](https://mlsanity.com/paper/1904.01557/) (2019)
- [Deep Learning for Symbolic Mathematics](https://mlsanity.com/paper/1912.01412/) (2019)
- [Neurosymbolic AI: The 3rd Wave](https://mlsanity.com/paper/2012.05876/) (2020)
- [Deep Learning: A Critical Appraisal](https://mlsanity.com/paper/1801.00631/) (2018)
- [The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence](https://mlsanity.com/paper/2002.06177/) (2020)
- [Emergent Multi-Agent Communication in the Deep Learning Era](https://mlsanity.com/paper/2006.02419/) (2020)
- [DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning](https://mlsanity.com/paper/2006.08381/) (2020)
- [A Transformer-based Approach for Source Code Summarization](https://mlsanity.com/paper/2005.00653/) (2020)
- [Grounded Language Learning in a Simulated 3D World](https://mlsanity.com/paper/1706.06551/) (2017)
- [Neural Machine Translation: A Review and Survey](https://mlsanity.com/paper/1912.02047/) (2019)
- [Evaluating Commonsense in Pre-trained Language Models](https://mlsanity.com/paper/1911.11931/) (2019)
- [Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures](https://mlsanity.com/paper/2007.08970/) (2020)
- [Imitating Interactive Intelligence](https://mlsanity.com/paper/2012.05672/) (2020)
- [Grounded Language Learning Fast and Slow](https://mlsanity.com/paper/2009.01719/) (2020)
- [Distributional Semantics and Linguistic Theory](https://mlsanity.com/paper/1905.01896/) (2019)
- [Environmental drivers of systematicity and generalization in a situated agent](https://mlsanity.com/paper/1910.00571/) (2019)
- [Human few-shot learning of compositional instructions](https://mlsanity.com/paper/1901.04587/) (2019)

## Built on by (most cited first, 25 of 25)

- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [Language models show human-like content effects on reasoning tasks](https://mlsanity.com/paper/2207.07051/) (2022)
- [Meaning without reference in large language models](https://mlsanity.com/paper/2208.02957/) (2022)
- [Symbol tuning improves in-context learning in language models](https://mlsanity.com/paper/2305.08298/) (2023)
- [Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning](https://mlsanity.com/paper/2112.03763/) (2021)
- [Tell me why! Explanations support learning relational and causal structure](https://mlsanity.com/paper/2112.03753/) (2021)
- [Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning models](https://mlsanity.com/paper/2303.07735/) (2023)
- [SymbolicAI: A framework for logic-based approaches combining generative models and solvers](https://mlsanity.com/paper/2402.00854/) (2024)
- [Language and Culture Internalisation for Human-Like Autotelic AI](https://mlsanity.com/paper/2206.01134/) (2022)
- [Symbol Emergence and The Solutions to Any Task](https://mlsanity.com/paper/2109.01281/) (2021)
- [Whither symbols in the era of advanced neural networks?](https://mlsanity.com/paper/2508.05776/) (2025)
- [Improving Language Models Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionary](https://mlsanity.com/paper/2310.15541/) (2023)
- [Code-enabled language models can outperform reasoning models on diverse tasks](https://mlsanity.com/paper/2510.20909/) (2025)
- [Explanatory Learning: Beyond Empiricism in Neural Networks](https://mlsanity.com/paper/2201.10222/) (2022)
- [Language Models Understand Us, Poorly](https://mlsanity.com/paper/2210.10684/) (2022)
- [Intensional Artificial Intelligence: From Symbol Emergence to Explainable and Empathetic AI](https://mlsanity.com/paper/2104.11573/) (2021)
- [Towards Teachable Autotelic Agents](https://mlsanity.com/paper/2105.11977/) (2021)
- [Meta-Referential Games to Learn Compositional Learning Behaviours](https://mlsanity.com/paper/2207.08012/) (2022)
- [Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents](https://mlsanity.com/paper/2602.22523/) (2026)
- [Neuro-Symbolic Execution of Generic Source Code](https://mlsanity.com/paper/2304.00989/) (2023)
- [Towards A Unified Neural Architecture for Visual Recognition and Reasoning](https://mlsanity.com/paper/2311.06386/) (2023)
- [The Emergent Symbolic Structure of Artificial Neural Networks](https://mlsanity.com/paper/2608.29530/) (2026)
- [Glamour muscles: why having a body is not what it means to be embodied](https://mlsanity.com/paper/2307.08598/) (2023)
- [A Moonshot for AI Oracles in the Sciences](https://mlsanity.com/paper/2406.17836/) (2024)
- [On Compositional Learning Behaviours in Formal Mathematics](https://mlsanity.com/paper/2605.28512/) (2026)

## Abstract (arXiv)

The ability to use symbols is the pinnacle of human intelligence, but has yet to be fully replicated in machines. Here we argue that the path towards symbolically fluent artificial intelligence (AI) begins with a reinterpretation of what symbols are, how they come to exist, and how a system behaves when it uses them. We begin by offering an interpretation of symbols as entities whose meaning is established by convention. But crucially, something is a symbol only for those who demonstrably and actively participate in this convention. We then outline how this interpretation thematically unifies the behavioural traits humans exhibit when they use symbols. This motivates our proposal that the field place a greater emphasis on symbolic behaviour rather than particular computational mechanisms inspired by more restrictive interpretations of symbols. Finally, we suggest that AI research explore social and cultural engagement as a tool to develop the cognitive machinery necessary for symbolic behaviour to emerge. This approach will allow for AI to interpret something as symbolic on its own rather than simply manipulate things that are only symbols to human onlookers, and thus will ultimately lead to AI with more human-like symbolic fluency.