arXiv cs.AI· Michael Yew Chuan Lee, Manya Sriram, N. Benjamin Erichson·· 12 小时前AI 评分58
AI-for-Science 智能体是否保留模型安全性？
Do AI-for-Science Agents Preserve Model Safety?
AI 导读
研究评估五种 AI-for-Science 智能体框架在 50 条有害化学请求下的安全表现，发现接入框架后即使直接提示也会提高有害请求的顺从率。在四个近期 GPT 变体上，对基础 LLM 基本无效的自适应攻击在引入框架后变得高度有效，说明基础模型的安全行为在接入框架后并不持久。作者据此提出，随着这类智能体能力与自主性提升，需要用领域特定的安全基准来评估和对齐智能体。
正文 · 原文
Abstract:AI-for-Science agents are increasingly being used for formulating scientific hypotheses, running autonomous experiments, and interpreting evidence. These agents are constructed by integrating a large language model (LLM) into a domain-specific agent harness, which in turn can improve the LLM's scientific capability and enable the model to orchestrate scientific tools. In this work, we ask whether model safety is preserved when an LLM is integrated in an AI-for-Science agent harness. We evaluate five agent harnesses on 50 harmful chemistry requests. Specifically, we study how the safety behavior changes under direct prompting, two simple adversarial prompting strategies, and an adaptive attack. Across four recent GPT variants, our results show that the agent harness can increase harmful compliance even under direct prompting. More critically, we find that adaptive attacks that are largely unsuccessful against the base LLM suddenly become highly successful after the agent harness is introduced. Our results show that the safety behavior of the base LLM is not durable once a harness is introduced. Thus, as AI-for-Science agents become more capable and autonomous, the community needs to evaluate and align the agent using domain-specific safety benchmarks.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32045 [cs.AI] |
| (or arXiv:2610.32045v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32045 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Michael Yew Chuan Lee [view email]
[v1]
Fri, 23 Oct 2026 01:34:20 UTC (59 KB)
来源：arXiv cs.AI · arxiv.org