Adversarial-Test-Driven Multi-Agent LLM Defense: A Self-Evolving Framework via Inference-Time Prompt Optimization

Abstract

Large Language Models (LLMs) remain highly susceptible to jailbreak attacks that bypass safety alignments through sophisticated prompt manipulation. While multi-agent defense systems have emerged as a promising countermeasure, existing frameworks predominantly rely on static agent designs, which struggle to adapt to evolving adversarial strategies. To bridge this gap, we propose an Adversarial-Test-Driven Multi-Agent Defense framework that shifts the focus from model-level fine-tuning to system-

Categories

Framework mappings

Suggested from the entry's categories.

@article{qu2026adversarialtestdriven,
  title = {{Adversarial-Test-Driven Multi-Agent LLM Defense: A Self-Evolving Framework via Inference-Time Prompt Optimization}},
  author = {Yang Qu and Yuwei He and Lei Cao and Juzheng Wang and Sulei Li and Hongxi Chen},
  year = {2026},
  month = may,
  journal = {Electronics},
  doi = {10.3390/electronics15112365},
  url = {https://www.semanticscholar.org/paper/cdc9ba46a28837d6157b523d6b784f9e2f82cca8}
}