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

华为论文提出让三类代理分工改进程序

AI 导读

研究中的 EvoTrias 将搜索规划、代码编写和评分交给不同代理,且不让编写代理读取评分器。在7项数学任务中,它有6项领先;相较4代理 CORAL,每次运行的 token 成本降低64%。这些结果针对代码优化任务,并非通用编程能力评测。

原帖引用 · 原文

该语言的正文暂不可用,当前显示已有版本。

@rohanpaul_ai

– https://t.co/HAaFbtSrck

Title: "Where Autonomy Belongs: A Separation of Powers for Agentic Program Evolution"

回复Rohan Paul@rohanpaul_ai
New Huawei paper finds that code-evolution agents do better and spend less when search planning, code writing, and scoring are handled by 3 separate owners. AlphaEvolve-style systems improve programs by writing code, scoring it, and picking what to try next. Some give the code writer little freedom, others let 1 coding agent steer the search at high token cost, and none hides the scorer. EvoTrias gives each job its own owner. A controller steers the search, a coding agent like Claude Code writes code, and an evaluator the agent cannot read scores it. On 7 math tasks it led 6 and cut token cost per run by 64% versus 4-agent CORAL. On OR-Tools, a 680K-line C++ repository, it lifted solver quality 13.2% on 300 instances, while 1-shot runs of the same agent averaged -0.1%. For code-optimizing agent loops, hide the scorer from the agent and keep search planning out of the coding agent.
在 X 查看这条帖子 ↗

来源:Rohan Paul · x.com

论文
发现内容有误?提交纠错