Planner-as-Router: Joint Plan-Time Model Routing for Cost-Efficient Multi-Agent Workflows

arXiv 2609.32917 ↗First posted 26 Sep 2026cs.AI cs.CL cs.MAcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks also fits: Tool learning and function calling

Abstract (arXiv)

Running large language model (LLM) agents in production gets expensive fast. A frontier model (the largest, most capable tier) is accurate but can cost 25 times what a small model costs per token, and the gap compounds once a workflow chains several calls together. Planner-as-Router (PaR) attacks this from a different angle. Instead of leaving model-tier selection to some component downstream, it folds the choice into planning itself. As the planner breaks a query into subtasks, it also assigns each one a model size tier (small, mid, or frontier, ordered by capability and price), so the dependencies between subtasks are visible before any specialist runs. Unlike per-call routers such as cascade routing, which look at one node at a time, PaR sees the whole workflow up front and needs no separate router model or training data. We evaluate PaR with EntBench, a benchmark of 54 enterprise agentic tasks across seven classes, graded by actually running the generated Structured Query Language (SQL) and MongoDB queries against live databases. Over 1,157 evaluations spanning eight routers and three seeds, PaR stays on the observed cost-accuracy frontier. It matches a sink-frontier heuristic (frontier model on terminal nodes only) in accuracy at comparable cost and a faithful FrugalGPT cascade at lower cost, and cuts cost 44% against all-frontier routing while giving up 2.9 points of accuracy. Several accuracy gaps fall inside the plus-or-minus six-point confidence interval of a 54-task study, so we frame PaR's advantage as frontier position rather than a clean accuracy win. We also report a preliminary observation, not a validated result: a small pilot hints that cheap routing may carry a hidden compounding penalty on compositional workflows, which we frame as a hypothesis for future measurement. PaR, EntBench, and all evaluation code are open source.

Key facts. No citing papers in the map yet (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 15 of its 19 references that are in the map. First posted on arXiv 26 Sep 2026.

Builds on

15 of 19 references.

Closest ancestors · 4

Same direction, newest first

2025MasRouter: Learning to Route LLMs for Multi-Agent Systems16 Feb
2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains17 Jun
2023A Survey on Large Language Model based Autonomous Agents22 Aug
2023AgentBench: Evaluating LLMs as Agents7 Aug

Other references · 11

2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
2023GAIA: a benchmark for General AI Assistantscited by 1,128
2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 372
2024RouterBench: A Benchmark for Multi-LLM Routing Systemcited by 238
2023AutoMix: Automatically Mixing Language Modelscited by 125

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way