Safety of Latent Communication in Multi-Agent Systems
Quick summary
arXiv:2609.39788v1 Announce Type: new Abstract: Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and latency overhead of text-based communication. To this end, lightweight trainable links are introduced to map the sender's representations into the receiver's input space. In this work, we show that even benign link training can increase harmful compliance relative to text-based communication while the underlying safety-aligned agents remain unchanged. An attacker can amplify this effect by optimi
Key takeaways
- arXiv:2609.39788v1 Announce Type: new Abstract: Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and latency overhead of text-based communication.
- To this end, lightweight trainable links are introduced to map the sender's representations into the receiver's input space.
- In this work, we show that even benign link training can increase harmful compliance relative to text-based communication while the underlying safety-aligned agents remain unchanged.
Why it matters
“Safety of Latent Communication in Multi-Agent Systems” shows why AI risk cannot be reduced to answer accuracy. Access controls, logging, human approval and incident response need to be designed into the workflow from the start.
Member comments