Research map / Multi-agent systems and games / Human-AI and goal-conditioned
A mathematical theory of cooperative communication
Pei Wang, Junqi Wang, Pushpi Paranamana, Patrick Shafto
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 full Sinkhorn scaling instead of one-step approximation | cooperative communication plans · Numeral interpretation | Cooperative Index: 0.5 -> 1 | Improved |
| use full Sinkhorn scaling instead of one-step approximation under common-ground perturbation | EOT plans · Dirichlet simulations, 100x100 | Cooperative Index | Improved |
| increase greediness lambda above 1 (ablation) | EOT plans · Perturbed 3x3 example | Cooperative Index: 0.41 -> 0.25 | Hurt |
| increase lambda from 0.1 to 40 (ablation) | EOT plans · 50x50 perturbed matrices | Cooperative Index gap vs unperturbed | Hurt |
| add linear approximation correction for perturbed M | SK plan re-estimation · Perturbed M, L1 error | L1 distance | Improved |
Closest papers by meaning
- Semantics and Spatiality of Emergent Communication (NeurIPS 2024 · similarity 0.86)
- Narrowing the Collaboration Gap, Probably (NeurIPS 2026 · similarity 0.85)
- T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integration (AAAI 2024 · similarity 0.85)
- More Capable, Less Cooperative? When LLMs Fail at Zero-Cost Collaboration (ICML 2026 · similarity 0.84)
- Learning to Communicate Through Implicit Communication Channels (ICLR 2025 · similarity 0.84)
- COOP$^2$: Defining, Observing, and Repairing Cooperation in LLM Multi-Agent Systems (NeurIPS 2026 · similarity 0.84)
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.
