Behavior Question Answering on Personal-VCL-Bench Behavior
35.71AccuracyAgentic Context Bank
Evaluation Results
| Method | Links | |
|---|---|---|
| Agentic Context BankContext regime=Ours, Backbone=Gemma-4-31B2026.05 | 35.71 | |
| Language-ctx (kmax)Context regime=Language-ctx (kmax), Backbone=Gemma-4-31B2026.05 | 34.69 | |
| No-contextContext regime=No-context, Backbone=Gemma-4-31B2026.05 | 29.59 | |
| Visual-ctx (kmax)Context regime=Visual-ctx (kmax), Backbone=Gemma-4-31B2026.05 | 27.55 |