Google 预印本:AI 记录改造日志实现自我改进
Google 这篇预印本让 AI 自己改 harness 并写改造日志,换模型也能接着跑,84.75 分对比 73.42 分的差距说明日志真的管用。做智能体工程的人可以直接抄这套日志方法,比每次换模型都重头调参省事多了。
Google 发布一篇预印本论文,让 AI 重写一个智能体 harness,并把每次改动的原因与效果记录成日志。
实验中先由 Opus 5.5 进行改造并留下日志,再换用 Gemini 3.
8 Flash 继续迭代。结果显示,有日志时模型在 workplace tasks 基准上得 84.
75 分,没有日志时只有 73.42 分;
编程任务上,带日志的版本在 10 次运行中有 9 次胜出。论文的核心结论是:更换新模型时不必从零开始改造 harness,改造知识可以通过日志跨模型传递,形成复利效应。
这意味着递归自我改进(Recursive self-improvement)的路径正在变得可行,工程经验从模型资产变成了可迁移的独立资产。
This is a super interesting paper and Recursive self-improvement keeps coming closer. New Google preprint:
Google had AI rewrite an agents harness and keep a log of every change, why it made it and whether it worked. Then they swapped Opus 5.5 for Gemini 3.8 Flash and let it keep going.
With the log: 84.75 on workplace tasks, without: 73.42. In coding it came out ahead in 9 of 10 runs.
tl;dr a new model no longer means starting from scratch. That's where it compounds.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Gemini 3.8 Flash, Opus 5.5, Google, agents.
Source attribution: curated from kimmonismus (@kimmonismus). Cross-source corroboration: 2 independent sources have covered this development (including Fireworks AI), confirming industry-wide signal strength.
- Fireworks AI11-17 19:40Source