mlsanityData to 14 Oct 2026

Interpretable Emergent Language Using Inter-Agent Transformers

arXiv 2505.02215 ↗First posted 4 May 2025cs.AI cs.CLcited by 1

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

Abstract (arXiv)

This paper explores the emergence of language in multi-agent reinforcement learning (MARL) using transformers. Existing methods such as RIAL, DIAL, and CommNet enable agent communication but lack interpretability. We propose Differentiable Inter-Agent Transformers (DIAT), which leverage self-attention to learn symbolic, human-understandable communication protocols. Through experiments, DIAT demonstrates the ability to encode observations into interpretable vocabularies and meaningful embeddings, effectively solving cooperative tasks. These results highlight the potential of DIAT for interpretable communication in complex multi-agent environments.

Key facts. Cited by 1 paper in the map (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 11 of its 14 references that are in the map. First posted on arXiv 4 May 2025.

Builds on

11 of 14 references.

References · 11

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  4. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 575
  5. 2016Learning Multiagent Communication with Backpropagationcited by 366
  6. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 263
  7. 2018TarMAC: Targeted Multi-Agent Communicationcited by 208
  8. 2018Learning Attentional Communication for Multi-Agent Cooperationcited by 175
  9. 2017Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbolscited by 125
  10. 2022A Survey of Multi-Agent Deep Reinforcement Learning with Communicationcited by 104
  11. 2018Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architecturescited by 30

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Wanting to Be Understood Explains the Meta-Problem of Consciousnesscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication
  2. 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs
  3. 2026HyLaT: Efficient Multi-Agent Communication via Hybrid Latent-Text Protocol
  4. 2026Emergent Language as an Approach to Conscious AI
  5. 2024Emergent Language: A Survey and Taxonomy
  6. 2024Fully Independent Communication in Multi-Agent Reinforcement Learning
  7. 2024Knowledge Distillation from Language-Oriented to Emergent Communication for Multi-Agent Remote Control
  8. 2024A Review of the Applications of Deep Learning-Based Emergent Communication