The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration

Documenti analoghi

• The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents
  di: Liu, Jiayuan, et al.
  Pubblicazione: (2026)
• MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate
  di: Amayuelas, Alfonso, et al.
  Pubblicazione: (2024)
• Multi-Agent Collaboration via Evolving Orchestration
  di: Dang, Yufan, et al.
  Pubblicazione: (2025)
• Multi-Agent Collaboration via Cross-Team Orchestration
  di: Du, Zhuoyun, et al.
  Pubblicazione: (2024)
• Agents that Matter: Optimizing Multi-Agent LLMs via Removal-Based Attribution
  di: Lu, Mingyu, et al.
  Pubblicazione: (2026)