Safety of Latent Communication in Multi-Agent Systems

arXiv:2609.39788 · cs.AI, cs.LG, cs.MA · Submitted 2026-09-30 · Read on arXiv

cs.AI, cs.LG, cs.MA

Submitted: 2026-09-30

Updated: 2026-10-05

Code: https://github.com/Muhammad-Huzaifaa/latent-safety

Terminology

• Multi-Agent System — 1× in this paper · explained in 6 episodes

Sources

• Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems
• StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Out of Sight, Not Out of Mind: Unveiling Latent Attack in Latent-based Multi-Agent Systems
• Universal and Transferable Adversarial Attacks on Aligned Language Models
• Recursive Multi-Agent Systems

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems