Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems

Documenti analoghi

• Convergence dynamics of Agent-to-Agent Interactions with Misaligned objectives
  di: Cosentino, Romain, et al.
  Pubblicazione: (2025)
• Conjunctive Prompt Attacks in Multi-Agent LLM Systems
  di: Arif, Nokimul Hasan, et al.
  Pubblicazione: (2026)
• Exposing Weak Links in Multi-Agent Systems under Adversarial Prompting
  di: Arora, Nirmit, et al.
  Pubblicazione: (2025)
• Influencing LLM Multi-Agent Dialogue via Policy-Parameterized Prompts
  di: Bo, Hongbo, et al.
  Pubblicazione: (2026)
• A Survey on Hypergame Theory: Modeling Misaligned Perceptions and Nested Beliefs for Multi-agent Systems
  di: Trencsenyi, Vince, et al.
  Pubblicazione: (2025)