跳到正文
RadarAI· X:Rohan Paul (@rohanpaul_ai)·· 2 小时前AI 评分55

Google 与宾州州立大学提出 SIM 自改进记忆方法

AI 导读

Google 与宾州州立大学论文提出 Self-Improvement Memory(SIM),在 AI 改写智能体 harness 代码时记录每次编辑针对的问题、推理过程和实测结果,供新模型读取以决定保留或修改旧编辑。

正文 · 原文

Rohan Paul· @rohanpaul_ai · X·2026-11-18 04:24· 53 分钟前AI 评分46

AI 导读

Google 与宾州州立大学论文提出 Self-Improvement Memory(SIM),在 AI 改写智能体 harness 代码时记录每次编辑针对的问题、推理过程和实测结果,供新模型读取以决定保留或修改旧编辑。

正文 · 原文

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.

来源:Rohan Paul · x.com

来源:RadarAI · aihot.news