论文40
UC Berkeley 与微软新法降低编码智能体 token 成本
原标题:New UC Berkeley and Microsoft paper cuts coding-agent token costs by 18.4% to 30.9% using an external controller that learns from past runs.
UC Berkeley 与微软提出外部控制器 TokenEconomizer,在 Claude Code、Codex 和 GitHub Copilot CLI 的 277 个 SWE-Bench 任务上将每任务平均成本降低 18.4% 至 30.9%。
中文译文尚未完成,先为你展示原文。
New UC Berkeley and Microsoft paper cuts coding-agent token costs by 18.4% to 30.9% using an external controller that learns from past runs.
by injecting learned facts, pruning unused tools, and stopping failed loops early.
Coding agents are billed by the token, and each turn resends the growing history, so long projects get expensive. Token efficiency is usually measured on isolated tasks, missing the cost that builds up across a sequence of tasks in the same codebase.
TokenEconomizer sits outside the agent as a black box, changing only prompts and tool settings. From past runs it learns which facts to inject, which unused tools to drop, and when to stop a failing loop.
Across Claude Code, Codex, and GitHub Copilot CLI on 277 SWE-Bench tasks, it cut mean per-task cost 18.4% to 30.9%. It improved Pass@1 in 4 of 5 agent-model settings, and savings held in every repository.
Measure agent cost across a whole project, not per task, and use an external controller that adapts to each repo, not fixed plugins.
同一件事的其他报道1 篇
微软研究院等发布 TokenEconomizer:让编码智能体从历史会话中学习以降低 token 成本
Microsoft Research · 原文
