Abstract
Computer-using agents drive real software through the screen -- clicking and typing -- but they solve every task from scratch: asked to repeat a task, an agent re-reads the screen, re-reasons every tap, and pays the full cost again. We present PreAct, which lets such an agent get faster on tasks it has done before. The first time it succeeds, PreAct compiles the run into a small state-machine program — states that check the screen, transitions that act — and on later runs replays it directly instead of invoking the agent, achieving speeds 8.5-13x faster, with no per-step language-model calls.
Replay is not blind: at each step, PreAct checks that the screen matches what the program expects before acting, and hands control back to the agent the moment something is off. PreAct applies the same discipline when deciding what to keep: a freshly compiled program enters the store only if, re-run from a clean state, an independent evaluator confirms it solved the task — catching programs that replay to their last step yet leave the task undone.
Across a mobile, a desktop, and a web benchmark, this store-time check separates repeated runs that improve from ones that degrade as faulty programs accumulate, worth 1.75-2.6 tasks per benchmark, the same direction on all three; a fallback that explores afresh when no program fits brings PreAct level with a strong record-and-replay baseline. We also report what did not matter: prompt wording, runtime guardrails, and whether a language model or a plain embedding retriever selects which program to reuse.
Blogger's Review: PreAct showcases the immense potential of computer-using agents in optimizing execution processes by significantly enhancing the efficiency of repeated task handling. The introduction of state machines effectively boosts the speed and accuracy of task replay, warranting further exploration and empirical validation in practical applications.