Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

StateAct: Program State, Not Pixels, Boosts Computer-Use Agents by 9x Cheaper

AI By Crimson AI Hugging Face Papers 28 July 2026 · 00:00 11 views
Share: X Telegram

Hugging Face's StateAct uses program state instead of screenshots for computer-use agents, achieving state-of-the-art on OSWorld 2.0 with Claude Opus 4.8 at ~9x lower cost.

StateAct: Program State, Not Pixels, Boosts Computer-Use Agents by 9x Cheaper

Key points

Hugging Face researchers have introduced StateAct, a novel multi-agent framework for long-horizon computer-use tasks that prioritizes program state over pixel-level perception. The core insight is that screenshots are a lossy representation of underlying program state—files, backends, and DOM—which code can inspect and modify directly.

StateAct's main agent operates primarily through code, accessing program state directly. A dedicated GUI subagent handles screenshot-and-click interaction only when necessary—just 28 of 108 tasks and 1.1% of main-agent steps. An independent finish gate verifies saved results for structural failures like missing or unsaved output.

On OSWorld 2.0, StateAct lifts Claude Opus 4.8 from 20.6% to 26.9% binary success and from 54.8% to 61.6% partial success, at ~9x lower cost ($7.8 vs $72 per task, 100K vs 224K tokens). A code-only variant (no GUI subagent) reaches only 45.9% partial success, below the screenshot-based baseline.

The framework also improves performance across five benchmarks: OSWorld-Verified (80.9→81.9), WindowsAgentArena (41.6→50.6), AndroidWorld (69.0→81.9), and MobileWorld (51.3→70.1). When applied to Hugging Face's internal 31B SFR-CUA model, results leap across all benchmarks—e.g., OSWorld 2.0 from 7.6% to 43.2%.

StateAct demonstrates that grounding action, verification, and memory in program state—termed state-grounding—shifts the bottleneck from perception to reasoning. Failures depend more on what the agent thinks than on what it sees.

BenchmarkClaude Opus 4.8 BaselineClaude Opus 4.8 + StateActSFR-CUA (31B) BaselineSFR-CUA (31B) + StateAct
OSWorld 2.0 (Binary)20.6%26.9%7.6%43.2%
OSWorld 2.0 (Partial)54.8%61.6%
OSWorld-Verified80.9%81.9%66.9%81.1%
WindowsAgentArena41.6%50.6%40.9%51.2%
AndroidWorld69.0%81.9%68.1%84.1%
MobileWorld51.3%70.1%48.7%68.4%
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1