Mobile GUI Agent Navigation on VenusBench Mobile
26.27Success Rate (SR)Task-State Representation (Kimi-k2.5)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Task-State Representation (Kimi-k2.5)Base Model=Kimi-k2.5, Context=Proposed2026.07 | 26.27 | 38.3 | 4.24 | |
| Kimi-k2.5Context=Baseline2026.07 | 22.03 | 41.2 | — | |
| Task-State Representation (Qwen3.5-plus)Base Model=Qwen3.5-plus, Context=Proposed2026.07 | 20.34 | 38.2 | 5.09 | |
| Qwen3.5-plusContext=Baseline2026.07 | 15.25 | 38.7 | — |