TokenEconomizer study uses an external controller to cut coding-agent token costs
A UC Berkeley and Microsoft paper proposes an external controller that learns from past coding-agent runs to inject useful facts, remove unused tools, and stop failing loops early. Across 277 SWE-Bench tasks using Claude Code, Codex, and GitHub Copilot CLI, the reported mean per-task cost fell by 18.4% to 30.9%.