In-context adaptation on Secretary
7.6Cumulative RewardCross-task RL
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Cross-task RLTraining Strategy=Cross-task RL, Backbone=Qwen3-8B2026.06 | 7.6 | 24 | 0.78 | |
| Single-task RLTraining Strategy=Single-task RL, Backbone=Qwen3-8B2026.06 | 7.07 | 3 | 0.72 | |
| Base (Qwen3-8B)Training Strategy=None (Base Model), Backbone=Qwen3-8B2026.06 | 4.58 | 15 | 0.46 |