Adaptive multi-agent topology collapses to six graphs, and sparser graphs cost more tokens.

Codebook Agent argues per-query topology design as conditional graph generation over the N×N adjacency space is misaligned with the problem, with three facts behind it. Topologies surviving a reward filter collapse to about six distinct graphs even as codebook capacity grows from 8 to 64. Edge count correlates negatively with token consumption (r ≈ -0.4), so sparsifying makes inference more expensive. And a message-passing scorer over agent-profile nodes is adjacency-invariant whenever agents share a profile, the default in published benchmarks, so it cannot rank candidates at all there.