# "LazImpa": Lazy and Impatient neural agents learn to communicate efficiently

arXiv: https://arxiv.org/abs/2010.01878 · HTML: https://mlsanity.com/paper/2010.01878/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2020.

## Built on by (most cited first, 23 of 23)

- [What Artificial Neural Networks Can Tell Us About Human Language Acquisition](https://mlsanity.com/paper/2208.07998/) (2022)
- [Context Limitations Make Neural Language Models More Human-Like](https://mlsanity.com/paper/2205.11463/) (2022)
- [Emergent Communication: Generalization and Overfitting in Lewis Games](https://mlsanity.com/paper/2209.15342/) (2022)
- [Emergent Communication for Understanding Human Language Evolution: What's Missing?](https://mlsanity.com/paper/2204.10590/) (2022)
- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [Generative Emergent Communication: Large Language Model is a Collective World Model](https://mlsanity.com/paper/2501.00226/) (2024)
- [The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation](https://mlsanity.com/paper/2511.02687/) (2025)
- [Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off](https://mlsanity.com/paper/2301.13083/) (2023)
- [Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments](https://mlsanity.com/paper/2311.04453/) (2023)
- [Referential communication in heterogeneous communities of pre-trained visual deep networks](https://mlsanity.com/paper/2302.08913/) (2023)
- [NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communication](https://mlsanity.com/paper/2407.13999/) (2024)
- [Language Evolution with Deep Learning](https://mlsanity.com/paper/2403.11958/) (2024)
- [Over-communicate no more: Situated RL agents learn concise communication protocols](https://mlsanity.com/paper/2211.01480/) (2022)
- [Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel](https://mlsanity.com/paper/2111.02827/) (2021)
- [Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication](https://mlsanity.com/paper/2406.07277/) (2024)
- [A framework for the emergence and analysis of language in social learning agents](https://mlsanity.com/paper/2305.02632/) (2023)
- [Semantics and Spatiality of Emergent Communication](https://mlsanity.com/paper/2411.10173/) (2024)
- [A Compressive-Expressive Communication Framework for Compositional Representations](https://mlsanity.com/paper/2501.19182/) (2025)
- [Unsupervised Acquisition of Discrete Grammatical Categories](https://mlsanity.com/paper/2503.18702/) (2025)
- [Emergent Compositional Communication for Latent World Properties](https://mlsanity.com/paper/2604.03266/) (2026)
- [ETHER: Aligning Emergent Communication for Hindsight Experience Replay](https://mlsanity.com/paper/2307.15494/) (2023)
- [A Knowledge-Based Language Model: Deducing Grammatical Knowledge in a Multi-Agent Language Acquisition Simulation](https://mlsanity.com/paper/2512.02195/) (2025)
- [Factors Influencing the Emergence of Dependency Length Minimization in Neural Agent Simulations](https://mlsanity.com/paper/2609.06025/) (2026)

## Abstract (arXiv)

Previous work has shown that artificial neural agents naturally develop surprisingly non-efficient codes. This is illustrated by the fact that in a referential game involving a speaker and a listener neural networks optimizing accurate transmission over a discrete channel, the emergent messages fail to achieve an optimal length. Furthermore, frequent messages tend to be longer than infrequent ones, a pattern contrary to the Zipf Law of Abbreviation (ZLA) observed in all natural languages. Here, we show that near-optimal and ZLA-compatible messages can emerge, but only if both the speaker and the listener are modified. We hence introduce a new communication system, "LazImpa", where the speaker is made increasingly lazy, i.e. avoids long messages, and the listener impatient, i.e.,~seeks to guess the intended content as soon as possible.