AI RESEARCH
The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems
arXiv CS.LG
•
ArXi:2602.15382v2 Announce Type: replace-cross Multi-Agent Systems (MAS) powered by Large Language Models have unlocked advanced collaborative reasoning, yet they remain bottlenecked by discrete text communication, which imposes runtime overhead and information quantization loss. While latent state transfer offers an alternative, existing approaches either assume homogeneous sender--receiver architectures or rely on pair-specific learned translators, limiting scalability across diverse model families with disjoint manifolds.