Year: 2026
Type: conference-paper
Abstract: Multi-agent LLM systems coordinate through natural-language messages that consume 40-60% of their token budget.Replacing these with structured graphs reduces cost but fails on tasks requiring adaptive reasoning.We propose Routed Graph Handoff, where a lightweight LLM router (155 tokens, 0.15% overhead) selects between a typed dependency graph and natural language for each delegation.On four benchmarks (1,050+ trajectories), the routed system matches or exceeds NL-only on every task: +12.7 pp on τ -retail at 3.2× compression (p<0.01),+8.7 pp on BrowseComp at 2.2× compression (p<0.05), and parity on BFCL and AppWorld.Without the router, graph-only delegation regresses 14.6 pp on Ap-pWorld; the router eliminates this at near-zero cost.A graph-aware executor prompt is required: the same schema without interpretation guidance yields no gain.An oracle analysis reveals 8.6 pp of additional headroom, motivating execution-time adaptive routing as future work.
Authors: Pratyay Banerjee, Ankit Chadha
Institution: Amazon (United States)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W7204452896