Negotiation on DESRD Emergency
65Success RateGame Theory
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Game TheoryBackbone=GPT-4o-mini2026.04 | 65 | 3.1 | 9.2 | |
| EmoMAS-BayesBackbone=GPT-4o-mini2026.04 | 65 | 26.7 | 19.5 | |
| Q-LearningBackbone=Qwen-7B2026.04 | 60 | 54.2 | 18.9 | |
| EmoMAS-BayesBackbone=Qwen-7B2026.04 | 60 | 56.3 | 20.7 | |
| EmoMAS-LLMBackbone=GPT-4o-mini2026.04 | 56 | 20.2 | 16.1 | |
| EmoMAS-LLMBackbone=Qwen-7B2026.04 | 55 | 50.2 | 15.8 | |
| Game TheoryBackbone=Qwen-7B2026.04 | 52 | 49.3 | 20.4 | |
| CoherenceBackbone=GPT-4o-mini2026.04 | 46 | 10.5 | 18.9 | |
| VanillaBackbone=Qwen-7B2026.04 | 45 | 41.5 | 19.5 | |
| Vanilla+PromptBackbone=Qwen-7B2026.04 | 42 | 45.2 | 20.2 | |
| Q-LearningBackbone=GPT-4o-mini2026.04 | 40 | 16.8 | 15.2 | |
| CoherenceBackbone=Qwen-7B2026.04 | 36 | 42.6 | 19.3 | |
| Vanilla+PromptBackbone=GPT-4o-mini2026.04 | 26 | 22.7 | 24.6 | |
| VanillaBackbone=GPT-4o-mini2026.04 | 25 | 21.6 | 24.5 |