Strategic Bargaining on Size-Prize Bargaining
0.8196BPDPO (pairs)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DPO (pairs)framework=GameTalk2026.01 | 0.8196 | 329.31 | 1.1503 | |
| GRPOframework=GameTalk2026.01 | 0.7514 | 176.28 | 2.0965 | |
| Untrainedframework=GameTalk2026.01 | 0.3773 | -334.42 | -0.8542 | |
| STaRframework=GameTalk2026.01 | 0.3437 | -323.02 | -0.6465 |