Tokeneconomizer cuts ai coding agent costs by up to 30 percent
TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents
Computation and Language
Summary
Coding assistants powered by AI can be expensive to use because they consume many tokens, which costs money. The authors noticed that these assistants often have repetitive costs that current methods can't reduce well, especially when working on long projects with many tasks. They created a tool called TokenEconomizer that smartly decides when to use certain skills, remove unnecessary tools, or stop wasting tokens in unproductive situations. This tool reduced token costs by 18 to 31 percent while keeping the success rate the same across different AI coding assistants and coding tasks.
What this means in practice
- •For software development teams: Reduce AI coding assistant costs over multiple project tasks while maintaining code quality using an external token management tool.
- •For security auditors: Lower token expenses in AI-assisted security code auditing by cutting persistent resource wastage through adaptive control.
Authors
Aaron J. Li, Weijia Xu, Chandan Singh, Zixiao Chen, Jeevana Priya Inala, Charlotte Siska, Acar Tamersoy, Bin Yu, Ion Stoica, Michel Galley, Jianfeng Gao
Abstract
Advances in frontier coding agents have sharply increased the token costs of AI-assisted software engineering. Their token efficiency is typically evaluated on isolated tasks, whereas real-world developers use them to continuously build, update, and maintain large-scale projects. This mismatch motivates us to evaluate agents over sequences of realistic coding tasks, where we find that agents exhibit recurring environment-dependent token costs that existing methods struggle to reduce. To minimize these costs, we introduce TokenEconomizer, an external controller that cuts environment-specific token costs over a sequence of tasks. These cuts come from determining (i) which operational micro-skills to inject, (ii) which persistently irrelevant tools to prune, and (iii) when to intervene in unproductive failure loops. Across Claude Code, Codex, and GitHub Copilot CLI paired with frontier models, TokenEconomizer reduces the average token cost by 18.4-30.9% with comparable task success. Savings hold in every repository under every tested agent-model setting and generalize to diverse domains such as sequential web development and security auditing, where costs fall by 6.4-21.2% depending on task structure. Our work establishes adaptive black-box cost control as a promising direction for reducing token costs of coding agents in realistic settings.