Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflows

Large Language Model (LLM)-based agentic systems have shown strong capabilities across various tasks. However, existing multiagent frameworks often rely on static or task-level workflows, which either over-process simple queries or underperform on complex ones, while also neglecting the efficiency-performance tradeoffs across heterogeneous LLMs. To address these limitations, we propose Difficulty-Aware Agentic Orchestration (DAAO), which can dynamically generate query-specific multi-agent workflows guided by predicted query difficulty. DAAO comprises three interdependent modules: a variational autoencoder (VAE) for difficulty estimation, a modular operator allocator, and a cost-and performanceaware LLM router. A self-adjusting policy updates difficulty estimates based on workflow success, enabling simpler workflows for easy queries and more complex strategies for harder ones. Experiments on six benchmarks demonstrate that DAAO surpasses prior multi-agent systems in both accuracy and inference efficiency, validating its effectiveness for adaptive, difficulty-aware reasoning.Our code is open-sourced at https://github.com/AutoAgents-ai/DAAO CCS Concepts • Computing methodologies → Cooperation and coordination; Multi-agent systems.