TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient
TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient
TokenEconomizer is an open-source plugin from UC Berkeley, Microsoft Research, and Microsoft Security that learns from an agent's past sessions in a repository to cut waste without modifying the agent or its model. Across 277 SWE-Bench tasks and five agent-model combinations, it reduced average cost by 18.4–30.9%, with savings in all 30 repository-combination pairs and broadly stable success rates. It works through micro-skills, tool pruning, and failure-loop intervention, and also lowered costs on Web-Bench (16.0–21.2%) and security auditing (6.4–19.6%).
It offers a concrete, evaluated method for cutting AI coding agent token costs without changing the underlying model, with per-repository results and an open-source implementation.
Source: Microsoft Research · microsoft.com