VISTA: A Visual Harness for Reasoning in an Interactive World
[Sztuczna inteligencja] Autorzy: Qiushi Han, Keya Hu, Linlu Qiu i 2 więcej
We show that multimodal models possess strong reasoning abilities and that an appropriate harness can unlock their potential to solve tasks across diverse interactive environments. We introduce VISTA, a visual harness that gives a general-purpose multimodal model long-horizon vision. VISTA allows the model to directly perceive the environment through visual observations and maintains a lossless visual memory that preserves past observations in their original form. The model can actively retrieve these observations and reorganize its visual input as it reasons. On ARC-AGI-3, VISTA improves Claude Opus 5.0's Relative Human Action Efficiency score from 40.68 to a perfect 100.00, with the model completing all 25 public games using 57.4% fewer actions than first-time human participants. VISTA's simple design also allows it to extend naturally to diverse visual environments with minimal adapt…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja