paperDecember 2025Unreviewed

DREAM: Dynamic Red-teaming across Environments for AI Models

Liming Lu, Xiang Gu, Junyu Huang, Jiawei Du, Xu Zheng, Yunhuai Liu, Yongbin Zhou, Shuchao Pang

Abstract

Large Language Models (LLMs) are increasingly used in agentic systems, where their interactions with diverse tools and environments create complex, multi-stage safety challenges. However, existing benchmarks mostly rely on static, single-turn assessments that miss vulnerabilities from adaptive, long-chain attacks. To fill this gap, we introduce DREAM, a framework for systematic evaluation of LLM agents against dynamic, multi-stage attacks. At its core, DREAM uses a Cross-Environment Adversarial

Framework mappings

NIST AI Risk Management Framework

MEASUREMeasure

Suggested from the entry's categories.

Cite

@misc{lu2025dream,
  title = {{DREAM: Dynamic Red-teaming across Environments for AI Models}},
  author = {Liming Lu and Xiang Gu and Junyu Huang and Jiawei Du and Xu Zheng and Yunhuai Liu and Yongbin Zhou and Shuchao Pang},
  year = {2025},
  month = dec,
  eprint = {2512.19016},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/8e63fb4190d0bb96927a6d4354d291254f90e042}
}