aifollow.news
Back Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · Original publication time AI score54

Paper proposes Self-Improvement Memory to carry AI agent code changes across modelsMachine translation

AI introduction

A paper attributed to Google and Penn State proposes Self-Improvement Memory (SIM), which records why an agent’s instruction and tool code was changed and how each edit performed, so those records can guide changes after a model switch. In the described workspace tasks, the score rose from 68.41 to 84.75, compared with 73.42 without the log. The reported result is limited to the tests described.

Original post · AI translation

@rohanpaul_ai
Translation · refer to the original

– https://t.co/9LOFeRirrf

标题:“自我改进记忆使持续递归自我改进成为可能”

ReplyRohan Paul@rohanpaul_ai
Translation
谷歌和宾夕法尼亚州立大学的一篇新论文发现,当一个 AI 重写为另一个 AI 提供指令和工具的代码时,记录每次修改的原因有助于让改进效果延续到新模型。 大语言模型现在可以重写智能体的运行框架,也就是运行提示词和工具的代码。切换模型或基准测试后,它的得分可能低于原版,而代码本身无法说明当初为何做出这些修改。 自我改进记忆(SIM)会记录每次修改所针对的问题、修改理由和测得的结果。优化器在新配置下读取这份日志,以决定保留还是调整哪些旧修改。 当 Claude Opus 5.5 的运行框架转用于 Gemini 3.8 Flash 的工作区任务时,SIM 将其得分从 68.41 提升到 84.75;没有日志时得分为 73.42。在 10 次重复的编程运行中,SIM 有 9 次领先,平均领先 2.36 分。 记录每次运行框架修改的原因及其得分,并将这份日志带到新模型中。
Original

New Google and Penn State paper finds that when one AI rewrites the code that gives another AI its instructions and tools, keeping notes on why each change was made helps the gains carry over to a new model. LLMs can now rewrite an agent's harness, the code that runs prompts and tools. After a model or benchmark switch, it can score below the original, and its code hides why edits were made. Self-Improvement Memory, or SIM, logs each edit with the problem it targeted, its reasoning and its measured result. The optimizer reads this log on the new setup to decide which old edits to keep or revise. When a Claude Opus 5.5 harness moved to Gemini 3.8 Flash workspace tasks, SIM lifted it from 68.41 to 84.75, versus 73.42 without the log. Across 10 repeated coding runs, SIM finished ahead 9 times, by 2.36 points on average. Store why each harness edit was made and how it scored, and carry that log to new models.

View this post on X ↗

Source: Rohan Paul · x.com

Research
Found an error? Send a correction