Routed Graph Handoff: Adaptive Format Selection for Multi-Agent LLM Delegation

2026-08-25

AI Summary

为解决多代理LLM系统中自然语言消息消耗大量token的问题，提出Routed Graph Handoff方法，通过轻量级LLM路由选择最合适的通信格式，有效提升性能并降低成本。

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 \textbf{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: \textbf{+12.7\,pp} on $τ$-retail at 3.2$\times$ compression ($p{<}0.01$), \textbf{+8.7\,pp} on BrowseComp at 2.2$\times$ compression ($p{<}0.05$), and parity on BFCL and AppWorld. Without the router, graph-only delegation regresses 14.6\,pp on AppWorld; 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.

Problem

• Multi-Agent LLM
• Token Budget
• Structured Graphs
• Adaptive Reasoning

Innovation

• Routed Graph Handoff
• adaptive format selection
• multi-agent LLM
• typed dependency graph
• communication efficiency