# Semantic Communication meets System 2 ML: How Abstraction, Compositionality and Emergent Languages Shape Intelligence

arXiv: https://arxiv.org/abs/2505.20964 · HTML: https://mlsanity.com/paper/2505.20964/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 56 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 30 of 31)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [GFlowNet Foundations](https://mlsanity.com/paper/2111.09266/) (2021)
- [Neurosymbolic AI: The 3rd Wave](https://mlsanity.com/paper/2012.05876/) (2020)
- [Deep Learning: A Critical Appraisal](https://mlsanity.com/paper/1801.00631/) (2018)
- [Inverse Scaling: When Bigger Isn't Better](https://mlsanity.com/paper/2306.09479/) (2023)
- [Biological Sequence Design with GFlowNets](https://mlsanity.com/paper/2203.04115/) (2022)
- [Emergent Multi-Agent Communication in the Deep Learning Era](https://mlsanity.com/paper/2006.02419/) (2020)
- [A Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research Problems](https://mlsanity.com/paper/1902.10265/) (2019)
- [Bayesian Structure Learning with Generative Flow Networks](https://mlsanity.com/paper/2202.13903/) (2022)
- [The Consciousness Prior](https://mlsanity.com/paper/1709.08568/) (2017)
- [Measuring Compositionality in Representation Learning](https://mlsanity.com/paper/1902.07181/) (2019)
- [Can Large Language Models Reason and Plan?](https://mlsanity.com/paper/2403.04121/) (2024)
- [Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?](https://mlsanity.com/paper/2502.15657/) (2025)
- [On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence](https://mlsanity.com/paper/2207.04630/) (2022)
- [Geometric Signatures of Compositionality Across a Language Model's Lifetime](https://mlsanity.com/paper/2410.01444/) (2024)
- [A Complexity-Based Theory of Compositionality](https://mlsanity.com/paper/2410.14817/) (2024)
- [Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach](https://mlsanity.com/paper/2502.01145/) (2025)
- [Learning Latent Wireless Dynamics from Channel State Information](https://mlsanity.com/paper/2409.10045/) (2024)
- [PORT: Preference Optimization on Reasoning Traces](https://mlsanity.com/paper/2406.16061/) (2024)
- [An STL-based Approach to Resilient Control for Cyber-Physical Systems](https://mlsanity.com/paper/2211.02794/) (2022)
- [A Mathematical Characterization of Minimally Sufficient Robot Brains](https://mlsanity.com/paper/2308.09041/) (2023)
- [Bayesian Inverse Contextual Reasoning for Heterogeneous Semantics-Native Communication](https://mlsanity.com/paper/2306.06403/) (2023)
- [Resilient-By-Design: A Resiliency Framework for Future Wireless Networks](https://mlsanity.com/paper/2410.23203/) (2024)
- [Topological Information Data Analysis](https://mlsanity.com/paper/1907.04242/) (2019)
- [Discrete, compositional, and symbolic representations through attractor dynamics](https://mlsanity.com/paper/2310.01807/) (2023)

## Built on by (most cited first, 2 of 2)

- [Resilient-native and Intelligent NextG Systems](https://mlsanity.com/paper/2506.12795/) (2025)
- [Logic-Driven Semantic Communication for Resilient Multi-Agent Systems](https://mlsanity.com/paper/2601.06733/) (2026)

## Abstract (arXiv)

The trajectories of 6G and AI are set for a creative collision. However, current visions for 6G remain largely incremental evolutions of 5G, while progress in AI is hampered by brittle, data-hungry models that lack robust reasoning capabilities. This paper argues for a foundational paradigm shift, moving beyond the purely technical level of communication toward systems capable of semantic understanding and effective, goal-oriented interaction. We propose a unified research vision rooted in the principles of System-2 cognition, built upon three pillars: Abstraction, enabling agents to learn meaningful world models from raw sensorimotor data; Compositionality, providing the algebraic tools to combine learned concepts and subsystems; and Emergent Communication, allowing intelligent agents to create their own adaptive and grounded languages. By integrating these principles, we lay the groundwork for truly intelligent systems that can reason, adapt, and collaborate, unifying advances in wireless communications, machine learning, and robotics under a single coherent framework.