mlsanityData to 14 Oct 2026

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

arXiv 2608.25277 ↗First posted 26 Aug 2026cs.CL cs.AIcited by 2

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

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 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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 8 of its 16 references that are in the map. First posted on arXiv 26 Aug 2026.

Builds on

8 of 16 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains17 Jun
  2. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 6

  1. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  2. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  3. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
  4. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 647
  5. 2024AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agentscited by 401
  6. 2024LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compressioncited by 348

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agentscited by 0
  2. 2026BRIDGE: Selective Boundary Repair with Dependency Graph Evidence in Multi-Agent Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
  2. 2026TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
  3. 2025DiSRouter: Distributed Self-Routing for LLM Selections
  4. 2026When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning
  5. 2026Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation
  6. 2025AMAS: Adaptively Determining Communication Topology for LLM-based Multi-Agent System
  7. 2026Training-Free Agentic AI: Probabilistic Control and Coordination in Multi-Agent LLM Systems
  8. 2026Runtime Burden Allocation for Structured LLM Routing in Agentic Expert Systems: A Full-Factorial Cross-Backend Methodology