$\textit{Agents Under Siege}$: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks

Documenti analoghi

• Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems
  di: Zhang, Guibin, et al.
  Pubblicazione: (2024)
• Conjunctive Prompt Attacks in Multi-Agent LLM Systems
  di: Arif, Nokimul Hasan, et al.
  Pubblicazione: (2026)
• HiveMind: Contribution-Guided Online Prompt Optimization of LLM Multi-Agent Systems
  di: Xia, Yihan, et al.
  Pubblicazione: (2025)
• Insider Attacks in Multi-Agent LLM Consensus Systems
  di: Sun, Xiaolin, et al.
  Pubblicazione: (2026)
• Pancake: Hierarchical Memory System for Multi-Agent LLM Serving
  di: Hu, Zhengding, et al.
  Pubblicazione: (2026)