
- 谁
- Microsoft Research, UC Berkeley, and Microsoft Security
- 引文
TokenEconomizer lowered the average cost by 18.4–30.9%, as shown in Figure 3, and saved the most in all 30 repository-combination pairs without performance loss.
发生了什么
微软研究院(Microsoft Research)及其合作者推出了 TokenEconomizer,这是一款开源插件,已在跨越 6 个代码库和 5 种 AI 编程代理与模型组合的 277 项 SWE-Bench 任务上进行了评估。该插件将平均成本降低了 18.4–30.9%,并且在第 6 项任务时,所有代码库的累计成本均低于默认水平。该论文还报告称,在连续的 Web 开发和安全审计任务中也降低了成本。
推荐理由
编程团队可以在同一代码库的重复性工作中降低代理成本,即使系统在没有会话历史的情况下启动,成本节省也会在第 6 项任务时显现。
接下来读什么
查看这件事的完整进展Microsoft Research and Collaborators Release TokenEconomizer to Cut AI Coding Agent Costs这件事到目前为止
Microsoft Research, UC Berkeley, and Microsoft Security introduced TokenEconomizer, an open-source plugin that uses repository session history to cut AI coding agent costs, and reported average cost reductions of 18.4–30.9% without performance loss in an evaluation of 277 SWE-Bench tasks. Across six repositories and five agent-and-model combinations, the plugin saved the most in all 30 repository-combination pairs, with cumulative costs falling below the default in every repository by the sixth task after starting with no prior session history. The researchers said TokenEconomizer also lowered costs on sequential web development and security auditing. Designed to run alongside existing AI coding agents without modifying their underlying models, the plugin requires no API key of its own and keeps what it learns on the developer's machine.
