microsoft/TokenEconomizer

Aaron J. Li1, Weijia Xu2, Chandan Singh2, Zixiao Chen3, Jeevana Priya Inala2, Charlotte Siska3, Acar Tamersoy3, Bin Yu1, Ion Stoica1, Michel Galley2, Jianfeng Gao2 1UC Berkeley   2Microsoft Research   3Microsoft Security Our measurement on SWE-Bench tasks: 18.4–30.9% lower mean cost across five agent–model combinations, cheaper in all 30 repository × combination cells, and Pass@1 up in 4 of 5. Results TokenEconomizer makes coding agents cheaper to run in the repositories you work in often, without changing the agent itself. It learns from the sessions an agent has already run in a repository, and uses that experience to cut waste in the sessions that follow. It has three mechanisms: facts: a build step that must run first, the spelling of a command that works here (python -m pytest where pytest is missing, npx tsc where tsc is), an environment variable a command needs, where generated files live. Micro-skills learns such…