Skip to content
NewA calmer, faster ZeroHour

VISTA: A Visual Harness for Reasoning in an Interactive World

arXiv cs.AI / cs.LG / cs.CLby Qiushi Han ()1 min read5 · 2 reads
AI summary · grok-4.7Summaries by Vani AI

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.

Key facts
  • 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.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at arxiv.org

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.

arXiv cs.AI / cs.LG / cs.CL

By Qiushi Han · arxiv.org

Read the full article at arXiv cs.AI / cs.LG / cs.CL

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.