TokenEconomizer：面向编程智能体的经验驱动黑盒成本控制

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

View PDF HTML (experimental)

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.

Subjects:	Computation and Language (cs.CL)
Cite as:	arXiv:2610.22732 [cs.CL]
	(or arXiv:2610.22732v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2610.22732 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Aaron Li [view email]
[v1] Thu, 15 Oct 2026 23:06:57 UTC (225 KB)