VISTA: A Visual Harness for Reasoning in an Interactive World
VISTA's visual-memory harness lifts Claude Opus 5.0 to a perfect ARC-AGI-3 score using 57.4% fewer actions.
VISTA is a visual harness that lets a general-purpose multimodal model observe an environment, keep past frames in lossless visual memory, and retrieve or reorganize that input while reasoning. On ARC-AGI-3 it raises Claude Opus 5.0's Relative Human Action Efficiency from 40.68 to 100.00, completing all 25 public games with 57.4% fewer actions than first-time human participants. With minimal adaptation, the same design substantially outperforms minimal harnesses on three additional visual game and puzzle benchmarks using the same underlying model.
- VISTA stores lossless visual memory and lets the model retrieve past observations.
- Claude Opus 5.0's ARC-AGI-3 efficiency score rises from 40.68 to 100.
- The model completes all 25 public games with 57.4% fewer actions than humans.
- The same harness beats minimal baselines on three further visual benchmarks.
From the original article
1 min read at arxiv.orgWe 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.
By Qiushi Han · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.