mlsanityData to 7 Oct 2026

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

arXiv 2010.01878 ↗First posted 5 Oct 2020cs.CL cs.AI cs.MAcited by 23

Not on the map. Why?

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.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 5; 2024: 6; 2025: 4; 2026: 2.

23 papers.

Sort:

By area:

  1. 2022What Artificial Neural Networks Can Tell Us About Human Language Acquisitioncited by 97
  2. 2022Context Limitations Make Neural Language Models More Human-Likecited by 32
  3. 2022Emergent Communication: Generalization and Overfitting in Lewis Gamescited by 28
  4. 2022Emergent Communication for Understanding Human Language Evolution: What's Missing?cited by 23
  5. 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
  6. 2024Generative Emergent Communication: Large Language Model is a Collective World Modelcited by 15
  7. 2023Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-offcited by 12
  8. 2023Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segmentscited by 11
  9. 2025The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperationcited by 11
  10. 2023Referential communication in heterogeneous communities of pre-trained visual deep networkscited by 10
  11. 2024NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communicationcited by 8
  12. 2024Language Evolution with Deep Learningcited by 5
11 more
  1. 2022Over-communicate no more: Situated RL agents learn concise communication protocolscited by 4
  2. 2021Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channelcited by 3
  3. 2024Speaking Your Language: Spatial Relationships in Interpretable Emergent Communicationcited by 3
  4. 2023A framework for the emergence and analysis of language in social learning agentscited by 2
  5. 2024Semantics and Spatiality of Emergent Communicationcited by 2
  6. 2025A Compressive-Expressive Communication Framework for Compositional Representationscited by 1
  7. 2025Unsupervised Acquisition of Discrete Grammatical Categoriescited by 1
  8. 2026Emergent Compositional Communication for Latent World Propertiescited by 1
  9. 2023ETHER: Aligning Emergent Communication for Hindsight Experience Replaycited by 0
  10. 2025A Knowledge-Based Language Model: Deducing Grammatical Knowledge in a Multi-Agent Language Acquisition Simulationcited by 0
  11. 2026Factors Influencing the Emergence of Dependency Length Minimization in Neural Agent Simulationscited by 0