SOURCE-LINKED INTELLIGENCE

Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Adapting the communication topology of an LLM multi-agent system to each query improves both accuracy and efficiency, yet current designers treat this as conditional graph generation: a variational, autoregressive, or diffusion decoder searches the $N \times N$ adjacency space, and a graph-network proxy trained on utility and a structural cost such as edge count ranks the sampled candidates. We argue that this formulation is misaligned with the problem. Empirically, topologies that survive a reward filter collapse to about six distinct graphs even when the codebook capacity grows from 8 to 64;

Read original source ↗ Open in workspace

recordType

paper

region

Global