# Characterizing tradeoffs between teaching via language and demonstrations in multi-agent systems

arXiv: https://arxiv.org/abs/2305.11374 · HTML: https://mlsanity.com/paper/2305.11374/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 19 May 2023.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Emergent Multi-Agent Communication in the Deep Learning Era](https://mlsanity.com/paper/2006.02419/) (2020)
- [Compositionality and Generalization in Emergent Languages](https://mlsanity.com/paper/2004.09124/) (2020)
- [Anti-efficient encoding in emergent communication](https://mlsanity.com/paper/1905.12561/) (2019)
- [Emergent Communication of Generalizations](https://mlsanity.com/paper/2106.02668/) (2021)
- [Characterizing the dynamics of learning in repeated reference games](https://mlsanity.com/paper/1912.07199/) (2019)
- [Extending rational models of communication from beliefs to actions](https://mlsanity.com/paper/2105.11950/) (2021)

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

- [TPD: Enhancing Student Language Model Reasoning via Principle Discovery and Guidance](https://mlsanity.com/paper/2401.13849/) (2024)
- [Rule-Guided Feedback: Enhancing Reasoning by Enforcing Rule Adherence in Large Language Models](https://mlsanity.com/paper/2503.11336/) (2025)

## Abstract (arXiv)

Humans teach others about the world through language and demonstration. When might one of these modalities be more effective than the other? In this work, we study the factors that modulate the effectiveness of language vs. demonstration using multi-agent systems to model human communication. Specifically, we train neural network agents to teach via language or demonstration in a grounded communication task, manipulating 1) the inherent difficulty of the task and 2) the competence of the teacher. We find that teaching by demonstration is more effective in the simplest settings, but language is more effective as task difficulty increases, due to its ability to generalize more effectively to unseen scenarios. Overall, these results provide converging evidence for a tradeoff between language and demonstration as teaching modalities in humans, and make the novel predictions that demonstration may be optimal for easy tasks, while language enables generalization in more challenging settings.