StateAct: Program State Cuts Agent Costs by 9x, Sets New SOTA
_akhaliq · x · 2026-07-28
While current computer-use agents rely heavily on vision models to read screen pixels, StateAct proposes a counterintuitive approach: using program state (such as files, backends, and DOM) as the primary interface, only invoking a GUI specialist for the 1.1% of steps that truly require visual judgment.
This "look less" approach sets a new SOTA on the OSWorld 2.0 benchmark. Using the exact same Claude Opus 4.8, the method increased task success rates from 20.6% to 26.9% while drastically reducing token consumption (from 224K to 100K), slashing cost-per-task from $72 to $7.8.
Furthermore, the framework is model-agnostic; dropping in an internal 31B model (SFR-CUA) yielded significant leaps across multiple benchmarks.
More from coding & agent
- Gemini shown off modding Minecraft to turn players into any Spider-Man — zacharynado · 2026-10-16
- IBM engineer maps 5 levels of AI coding, from manual to a 3-day agent software factory — TejasKumar_ · 2026-10-16
- 10 open-source repos that let your AI agent reverse-engineer apps and games — victor_explore · 2026-10-16
- The new CTO job: agent management and QA loops, 'cable management' instead of coding — HankYeomans · 2026-10-16
- Why company AI agents go stale: adoption needs in-house knowledge, not just better agents — EdenEmarco177 · 2026-10-16
- Open-source MCP lets coding agents search Obsidian's 9,000-plugin directory before reinventing wheels — pitfa19 · 2026-10-16