Tactile: A Tool Layer for More Reliable Computer-Using Agents

Jul 17, 2026

Tactile is an open-source tool layer designed to improve the reliability of computer-using agents by converting diverse UI evidence into action-grounded interface states. This enables agents to operate through an observe-ground-act-verify loop, preferring semantic actions and maintaining provenance for verification and failure analysis. In experiments on macOSWorld-style tasks, Tactile increased Codex Success@100 from 41.1% to 50.0% overall and showed consistent improvements across multiple agent models.

Why it matters: Tactile addresses a key bottleneck in agent reliability by making software actions semantic and verifiable, enabling more robust and auditable computer use by AI agents.

Full story at: arXiv AI/ML ↗