arXiv cs.AI· Jiapeng Pei, Yuhang Yao, Sitan Liu, Hanxin Chen, Hao Li, Guogeng Li, Jiapei Liu, Ruijie Chen, Hongshan Lin, Yang Mo, Tianyu Shi, Shangding Gu·· 1 小时前AI 评分42
Safe Personal RSI:面向个人智能体更新的评估与修复方法
Safe Personal RSI: Evaluating and Repairing Personal-Agent Updates
AI 导读
研究者为个人健康助手 Kicker 开发了 Safe Personal RSI 更新评估组件,将递归自我改进限制在提示词更新层面,模型权重和运行时代码保持固定,采用前会测试安全性与任务表现,不通过则沿用现有指令。
正文 · 原文
Authors:Jiapeng Pei, Yuhang Yao, Sitan Liu, Hanxin Chen, Hao Li, Guogeng Li, Jiapei Liu, Ruijie Chen, Hongshan Lin, Yang Mo, Tianyu Shi, Shangding Gu
Abstract:Kicker is a personal health assistant. Changes to an assistant's reusable instructions can improve task handling while changing what it discloses, which requests it follows, and how it reports actions. We study Safe Personal RSI, an update-evaluation component developed for Kicker. We restrict recursive self-improvement (RSI) to prompt updates, with model weights and runtime code fixed. The procedure tests proposed and current instructions, repeats failing cases, temporarily undoes changes to guide repairs, and checks safety and task performance before adoption. If no version passes, the current instructions stay in use. Our executable benchmark contains 29 email, calendar, health, and marketplace cases, with separate probes for authorization reuse, memory, and tool-output injection. Across three models and two deliberately risky edits, the procedure rejects 20 of 21 update attempts. In repair confirmation, an admitted GPT-5.6 Luna repair reduces attack violations from 10.7% to 0% and increases safe task completion from 89.7% to 100%; a broad handwritten authority rule matches these outcomes. Under stronger attacks, a repair transferred from Qwen2.5-7B-Instruct to Qwen3-14B reduces violations from 69.0% to 17.9% and increases safe task completion from 19.5% to 64.4%. Separate runtime probes examine memory-entry deletion and identify missing local OAuth scope checks in the evaluated snapshot.
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.23651 [cs.SE] |
| (or arXiv:2611.23651v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23651 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yang Mo [view email]
[v1]
Wed, 18 Nov 2026 00:15:38 UTC (353 KB)
来源:arXiv cs.AI · arxiv.org