aifollow.news
返回 Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · 原发布时间 AI 评分54

UC Berkeley 与 Microsoft 论文提出外部控制器,降低编程代理 Token 成本

AI 导读

论文提出 TokenEconomizer:它在代理外部调整提示词和工具设置,从过往运行中学习注入哪些事实、移除哪些未使用工具,以及何时停止失败循环。在 277 项 SWE-Bench 任务中,Claude Code、Codex 和 GitHub Copilot CLI 的平均单任务成本降低 18.4% 至 30.9%;5 种代理与模型设置中有 4 种的 Pass@1 提高。

原帖引用 · 原文

@rohanpaul_ai

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.

来源:Rohan Paul · x.com

论文
发现内容有误?提交纠错