MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG

Abstract

Multimodal agentic retrieval-augmented generation (RAG) systems expand the attack surface beyond prompt injection to include text poisoning, image injection, direct-query attacks, and orchestrator-level tool manipulation. Existing red-teaming approaches are typically surface-specific and often recycle known attack templates; on text-poisoning benchmarks we measure 73-84% exact duplication. We present MIRROR, a unified cross-surface framework that performs memory-guided Monte Carlo tree search wh

Categories

Framework mappings

Suggested from the entry's categories.

@misc{singh2026mirror,
  title = {{MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG}},
  author = {Inderjeet Singh and Andrés Murillo and Motoyoshi Sekiya and Yuki Unno and Junichi Suga},
  year = {2026},
  month = jun,
  eprint = {2606.26793},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.26793}
}