Negotiation on SSD Medical
86Success RateVanilla
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| VanillaBackbone=GPT-4o-mini2026.04 | 86 | 85.7 | 7.7 | |
| EmoMAS-BayesBackbone=GPT-4o-mini2026.04 | 84 | 86.4 | 16.9 | |
| EmoMAS-LLMBackbone=GPT-4o-mini2026.04 | 80 | 83.5 | 10.2 | |
| Vanilla+PromptBackbone=GPT-4o-mini2026.04 | 77 | 57.1 | 11.1 | |
| Game TheoryBackbone=Qwen-7B2026.04 | 75 | 2.2 | 7.9 | |
| EmoMAS-BayesBackbone=Qwen-7B2026.04 | 75 | 33.7 | 22.9 | |
| Vanilla+PromptBackbone=Qwen-7B2026.04 | 69 | 29.5 | 21.2 | |
| VanillaBackbone=Qwen-7B2026.04 | 68 | 28.5 | 18.6 | |
| Q-LearningBackbone=Qwen-7B2026.04 | 60 | 3.7 | 8.9 | |
| EmoMAS-LLMBackbone=Qwen-7B2026.04 | 60 | 28.9 | 17.1 | |
| CoherenceBackbone=Qwen-7B2026.04 | 54 | 17.6 | 20.5 | |
| CoherenceBackbone=GPT-4o-mini2026.04 | 46 | 38.2 | 12.8 | |
| Game TheoryBackbone=GPT-4o-mini2026.04 | 45 | 42.8 | 16.2 | |
| Q-LearningBackbone=GPT-4o-mini2026.04 | 40 | 8.2 | 15.2 |