Abstract
Compiling GUI procedures that agents execute repeatedly into programs can reduce their token costs. However, measuring payback and deciding when to compile have two challenges. First, compilation costs are uncertain because attempts can require repair and still fail to produce a usable program. Second, future reuse is unknown because tasks may stop arriving or GUI drift may stop the program from working. To address these challenges, we propose PACE (Payback-Aware Compilation from Experience), a system with a measurement protocol and an online compilation algorithm. The measurement protocol records successful and failed compilation costs, and compares agent and program execution costs on matched task inputs to estimate per-use savings and payback counts. Using these measurements, the online algorithm compares estimated future savings with compilation costs, including failed attempts, based on past task arrivals and compilation outcomes. It checks execution and compilation charges against a cumulative budget determined by observed task arrivals before allowing either action. Under stated action-cost assumptions, total cost after each arrival is at most $1+ε$ times the cost of running every task with the agent. For successful compilation attempts, estimated payback counts excluding source agent runs are 2-16 uses. In simulations using recorded task arrivals, PACE reduces token costs by 17.3% compared with ReAct, 24.9% with the AutoRPA adaptation, and 17.3% with the ToolPro adaptation on average ($ε=0.25$).
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Ming, Y., Xu, J., Wu, Z., & Jia, X. (2026). When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token Efficiency. https://omanscience.com/en/articles/when-to-compile-a-computer-use-agent-measuring-payback-and-making-compilation-decisions-for-token-efficiency
MLA 9
Ming, Yulong, et al. "When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token Efficiency." https://omanscience.com/en/articles/when-to-compile-a-computer-use-agent-measuring-payback-and-making-compilation-decisions-for-token-efficiency.
Chicago (author–date)
Ming, Yulong, Jie Xu, Zihan Wu, and Xiaohua Jia. 2026. "When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token Efficiency." https://omanscience.com/en/articles/when-to-compile-a-computer-use-agent-measuring-payback-and-making-compilation-decisions-for-token-efficiency.
Harvard
Ming, Y., Xu, J., Wu, Z. and Jia, X. (2026) 'When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token Efficiency', Available at: https://omanscience.com/en/articles/when-to-compile-a-computer-use-agent-measuring-payback-and-making-compilation-decisions-for-token-efficiency.
Vancouver
Ming Y, Xu J, Wu Z, Jia X. When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token Efficiency. https://omanscience.com/en/articles/when-to-compile-a-computer-use-agent-measuring-payback-and-making-compilation-decisions-for-token-efficiency
IEEE
Y. Ming, J. Xu, Z. Wu, and X. Jia, "When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token Efficiency," https://omanscience.com/en/articles/when-to-compile-a-computer-use-agent-measuring-payback-and-making-compilation-decisions-for-token-efficiency.