Expansion-Contraction: A Multi-Agent Graph Traversal Pattern for Compound AI Systems

Abstract

Compound AI systems that coordinate multiple specialized agents offer a promising path for complex reasoning tasks, yet principled architectural patterns for multi-agent coordination over structured data remain under-explored. We introduce \textit{Expansion-Contraction}, a general-purpose multi-agent graph traversal pattern in which an expansion phase walks a domain graph outward from a query origin, dynamically spawning ephemeral specialist agents at each node, and a contraction phase aggregates their findings inward to produce a verdict. The pattern is domain-agnostic: agent topology emerges isomorphically from the data graph rather than being hand-designed, and each agent operates on a small local context---avoiding the context-window saturation that degrades single-agent approaches on large graphs. We instantiate the pattern for supply chain root cause analysis, integrating domain-specific tools with temporal lead-time propagation. Across eight datasets (three real-world, five synthetic with controlled depth and width), Expansion-Contraction achieves 98.2\% accuracy on a production supply chain (624 cases) and 100\% on public benchmarks, outperforming single-agent baselines by 14+ percentage points while degrading gracefully as graph complexity increases. Investigation caching reduces token usage by up to 93.9\%, and concurrent path analysis yields up to 1.43$\times$ speedup. A production deployment demonstrates the pattern's viability for enterprise-scale agentic systems.