mlsanityData to 14 Oct 2026

Evaluating the relationship between regularity and learnability in recursive numeral systems using Reinforcement Learning

arXiv 2602.21720 ↗First posted 25 Feb 2026cs.CL cs.AIcited by 0

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

Human recursive numeral systems (i.e., counting systems such as English base-10 numerals), like many other grammatical systems, are highly regular. Following prior work that relates cross-linguistic tendencies to biases in learning, we ask whether regular systems are common because regularity facilitates learning. Adopting methods from the Reinforcement Learning literature, we confirm that highly regular human(-like) systems are easier to learn than unattested but possible irregular systems. This asymmetry emerges under the natural assumption that recursive numeral systems are designed for generalisation from limited data to represent all integers exactly. We also find that the influence of regularity on learnability is absent for unnatural, highly irregular systems, whose learnability is influenced instead by signal length, suggesting that different pressures may influence learnability differently in different parts of the space of possible numeral systems. Our results contribute to the body of work linking learnability to cross-linguistic prevalence.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 12 of its 47 references that are in the map. First posted on arXiv 25 Feb 2026.

Builds on

12 of 47 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Learning Efficient Recursive Numeral Systems via Reinforcement Learning11 Sep

Other references · 11

  1. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  2. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 575
  3. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 263
  4. 2016Multi-Agent Cooperation and the Emergence of (Natural) Languagecited by 185
  5. 2019The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agentscited by 26
  6. 2023What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structurecited by 13
  7. 2023Cultural evolution via iterated learning and communication explains efficient color naming systemscited by 10
  8. 2018Quantifying the dynamics of topical fluctuations in languagecited by 6
  9. 2021Learning Approximate and Exact Numeral Systems via Reinforcement Learningcited by 6
  10. 2025Recursive numeral systems are highly regular and easy to processcited by 2
  11. 2026Systematicity between Forms and Meanings across Languages Supports Efficient Communicationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Exploring Natural Language-Based Strategies for Efficient Number Learning in Children through Reinforcement Learning
  2. 2025Investigating the interaction of linguistic and mathematical reasoning in language models using multilingual number puzzles
  3. 2026The Effect of Scripts and Formats on LLM Numeracy
  4. 2024LLM The Genius Paradox: A Linguistic and Math Expert's Struggle with Simple Word-based Counting Problems
  5. 2022Overcoming Barriers to Skill Injection in Language Modeling: Case Study in Arithmetic
  6. 2025Emergent Abilities in Large Language Models: A Survey
  7. 2026Shared circuits predict whether LLMs generalize across formats in arithmetic reasoning
  8. 2024Comparing Rationality Between Large Language Models and Humans: Insights and Open Questions