VISTA: A Visual Harness for Reasoning in an Interactive World· VISTA：在一个互动世界中的视觉推理工具
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
VISTA：使多模态模型在互动环境中通过视觉观察进行高效推理的工具。
- 核心方法
- 引入VISTA，一个视觉工具，为多模态模型提供长远视觉感知和无损视觉记忆，允许模型主动检索和重组视觉输入。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 现有模型在互动环境中的视觉推理能力有限，无法有效利用历史观察数据。
- 关键实验
- 在ARC-AGI-3基准上的25个公开游戏中，VISTA使Claude Opus 5.0模型的相对人类行动效率得分提高到100.00，相比初次参与的人类参与者减少了57.4%的行动。
- 主要贡献
- 在ARC-AGI-3基准上显著提高了模型的推理效率，使其能以更少的动作完成所有游戏。
- 意义与局限
- VISTA为多模态模型在复杂互动环境中的应用提供了新的可能，但也可能面临不同环境下的泛化能力挑战。