How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909898462199808 |
|---|---|
| author | Ma, Zihan Zhu, Dongsheng Liu, Shudong Zhang, Taolin Liu, Junnan Li, Qingqiu Luo, Minnan Zhang, Songyang Chen, Kai |
| author_facet | Ma, Zihan Zhu, Dongsheng Liu, Shudong Zhang, Taolin Liu, Junnan Li, Qingqiu Luo, Minnan Zhang, Songyang Chen, Kai |
| contents | Current safety evaluations for LLM-driven agents primarily focus on atomic harms, failing to address sophisticated threats where malicious intent is concealed or diluted within complex tasks. We address this gap with a two-dimensional analysis of agent safety brittleness under the orthogonal pressures of intent concealment and task complexity. To enable this, we introduce OASIS (Orthogonal Agent Safety Inquiry Suite), a hierarchical benchmark with fine-grained annotations and a high-fidelity simulation sandbox. Our findings reveal two critical phenomena: safety alignment degrades sharply and predictably as intent becomes obscured, and a "Complexity Paradox" emerges, where agents seem safer on harder tasks only due to capability limitations. By releasing OASIS and its simulation environment, we provide a principled foundation for probing and strengthening agent safety in these overlooked dimensions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08487 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity Ma, Zihan Zhu, Dongsheng Liu, Shudong Zhang, Taolin Liu, Junnan Li, Qingqiu Luo, Minnan Zhang, Songyang Chen, Kai Multiagent Systems Computation and Language Current safety evaluations for LLM-driven agents primarily focus on atomic harms, failing to address sophisticated threats where malicious intent is concealed or diluted within complex tasks. We address this gap with a two-dimensional analysis of agent safety brittleness under the orthogonal pressures of intent concealment and task complexity. To enable this, we introduce OASIS (Orthogonal Agent Safety Inquiry Suite), a hierarchical benchmark with fine-grained annotations and a high-fidelity simulation sandbox. Our findings reveal two critical phenomena: safety alignment degrades sharply and predictably as intent becomes obscured, and a "Complexity Paradox" emerges, where agents seem safer on harder tasks only due to capability limitations. By releasing OASIS and its simulation environment, we provide a principled foundation for probing and strengthening agent safety in these overlooked dimensions. |
| title | How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity |
| topic | Multiagent Systems Computation and Language |
| url | https://arxiv.org/abs/2511.08487 |