Causal inference finds cheaper multi-agent communication topologies than the usual fully-connected default
arXiv·low signal
arXiv 2608.12921 (2026-08-13) uses causal inference to discover which edges in a multi-agent communication graph actually carry signal, then prunes the rest, producing topologies that are both cheaper and explainable. Across multiple reasoning and coding benchmarks the E2-Explainer framework substantially reduces communication cost while keeping task performance competitive. Since most multi-agent stacks default to broadcast or a fully-connected mesh and pay for every edge in tokens, edge-level attribution is the direct lever on cost.