Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Emergent communication in referential games
Studies languages that emerge between agents trained on referential and negotiation games.
50 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Human-AI and goal-conditioned, keyword cluster “communication · ai · collaboration”
State History Tried Checklist Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
10 papers in 2023–24 and 6 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 3.4% to 1.6%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Learning Multiagent Communication with Backpropagation (NeurIPS 2016 · 276 citations)
- 2017 · Multi-Agent Cooperation and the Emergence of (Natural) Language (ICLR 2017 · 116 citations)
- 2018 · Emergence of Grounded Compositional Language in Multi-Agent Populations (AAAI 2018 · 441 citations)
- 2019 · Ease-of-Teaching and Language Structure from Emergent Communication (NeurIPS 2019 · 27 citations)
- 2020 · Interactive Fiction Games: A Colossal Adventure (AAAI 2020 · 113 citations)
- 2021 · Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication (NeurIPS 2021 · 23 citations)
- 2022 · Emergent Graphical Conventions in a Visual Communication Game (NeurIPS 2022 · 5 citations)
- 2023 · Emergent Quantized Communication (AAAI 2023 · 4 citations)
- 2024 · Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication (NeurIPS 2024 · 6 citations)
- 2025 · Orpheus: Engineering Multiagent Systems via Communicating Agents (AAAI 2025 · 7 citations)
- 2026 · Representational Similarity and Model Behavior in Multi-Agent Interaction (ICML 2026 · 0 citations)
Earliest papers here
- Learning Multiagent Communication with Backpropagation (NeurIPS 2016 · 276 citations)
- Multi-Agent Cooperation and the Emergence of (Natural) Language (ICLR 2017 · 116 citations)
- Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols (NeurIPS 2017 · 54 citations)
What has been tried
45 papers here report 475 measured changes (a component added, removed or swapped, compared with a baseline): helped 58%, no clear effect 15%, hurt 23%, mixed 5%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Remove the communication gating function | Task environments in the gating ablation · task performance | Hurt | Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication (NeurIPS 2024 · 6 citations) | |
| Train the referential-game agents with input variation between Speaker and Listener using the random dataset, rather than the fixed dataset | Random-generator test set · representation classification accuracy | 84.4 (5.5) -> 100.0 (0.0) | Helped | Learning Multi-Object Positional Relationships via Emergent Communication (AAAI 2024 · 2 citations) |
| Add identified positional components to compositional messages | Compositional dictionary · accuracy | 22% ± 2% -> 30% ± 21%; maximum 28% -> 78% | Helped | Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication (NeurIPS 2024 · 1 citation) |
| Add a Decompose phase before Compose | Thing · accuracy | 0.273 -> 1.000 | Helped | CtD: Composition through Decomposition in Emergent Communication (ICLR 2025 · 0 citations) |
| Use utility maximization only, removing informativeness and complexity pressures | ManyNames · NID | 0.55 -> 0.84 | Hurt | Bridging semantics and pragmatics in information-theoretic emergent communication (NeurIPS 2024 · 0 citations) |
What reviewers will expect
Datasets and baselines named in the 10 papers of this approach from 2024–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- MNIST · 2 of 10 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 16 papers; from OpenAlex and the papers' affiliations).
- Technion - Israel Institute of Technology · 3 papers
- University of California, Berkeley · 2 papers
- Google DeepMind · 2 papers
- Inria · 2 papers
Use it
Download BibTeX of 32 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Human-AI coordination agents (125 papers)
- Collaborative multi-agent perception (86 papers)
- Boundedly rational agent modeling (87 papers)
- Theory-of-mind social reasoning (69 papers)
Elsewhere in the topic
- World-model-based agents (110 papers)
- Imitation and skill learning (100 papers)
- Language-grounded reinforcement agents (96 papers)
- Embodied agent learning (93 papers)
- Intrinsically motivated exploration (86 papers)
- Interactive multi-agent trajectory prediction (75 papers)
- Learning-guided MAPF search (73 papers)
- Vision-language navigation agents (66 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).