Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Multi-Agent Cooperation and the Emergence of (Natural) Language
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the informed rather than agnostic sender architecture | Referential-game agents · Referential game test, sm representation and vocabulary 100 | purity (%): 21 -> 46 | Helped |
| Use the informed rather than agnostic sender architecture | Referential-game agents · Referential game test, sm representation and vocabulary 100 | communication success (%): 99 -> 100 | Mixed |
| Show sender and receiver different images from the same target and distractor classes | Referential game · Referential game with image-level targets, informed sender, fc and vocabulary 100 | purity (%): 41 -> 45 | Helped |
| Show sender and receiver different images from the same target and distractor classes | Referential game · Referential game with image-level targets, agnostic sender, fc and vocabulary 100 | communication success (%): 99 -> 92 | Hurt |
| Add supervised image classification alongside referential-game play | Informed sender with fc representations and vocabulary 100 · Referential game with supervised ImageNet labeling | communication success | No clear effect |
| Add supervised image classification alongside referential-game play | Informed sender with fc representations and vocabulary 100 · Referential game with supervised ImageNet labeling | purity (%): 41 -> 70% | Helped |
| Add supervised image classification alongside referential-game play | Informed sender · ReferItGame image pairs, human evaluation | target image choice accuracy (%): 68% | Helped |
| Use the informed sender instead of the agnostic sender | Referential-game agents · Referential game test | symbols used: 2 -> 58 | Helped |
Closest papers by meaning
- Learning Multi-Object Positional Relationships via Emergent Communication (AAAI 2024 · similarity 0.89)
- Bridging semantics and pragmatics in information-theoretic emergent communication (NeurIPS 2024 · similarity 0.88)
- Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication (NeurIPS 2024 · similarity 0.88)
- Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication (NeurIPS 2024 · similarity 0.88)
- Multi-agent KTO: Enhancing Strategic Interactions of Large Language Model in Language Game (NeurIPS 2025 · similarity 0.88)
- Communicating Activations Between Language Model Agents (ICML 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.