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

arXiv: https://arxiv.org/abs/2509.11079 · HTML: https://mlsanity.com/paper/2509.11079/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 33 of its 68 references that are in the map.
- First posted on arXiv 14 Sep 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 33)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [Complexity-Based Prompting for Multi-Step Reasoning](https://mlsanity.com/paper/2210.00720/) (2022)
- [Data Interpreter: An LLM Agent For Data Science](https://mlsanity.com/paper/2402.18679/) (2024)
- [Multi-agent Architecture Search via Agentic Supernet](https://mlsanity.com/paper/2502.04180/) (2025)
- [GraphRouter: A Graph-based Router for LLM Selections](https://mlsanity.com/paper/2410.03834/) (2024)
- [EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms](https://mlsanity.com/paper/2406.14228/) (2024)
- [DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving](https://mlsanity.com/paper/2407.13690/) (2024)
- [MasRouter: Learning to Route LLMs for Multi-Agent Systems](https://mlsanity.com/paper/2502.11133/) (2025)
- [GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models](https://mlsanity.com/paper/2504.09696/) (2025)
- [Harder Tasks Need More Experts: Dynamic Routing in MoE Models](https://mlsanity.com/paper/2403.07652/) (2024)
- [AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions](https://mlsanity.com/paper/2410.20424/) (2024)
- [Archon: An Architecture Search Framework for Inference-Time Techniques](https://mlsanity.com/paper/2409.15254/) (2024)

## Built on by (most cited first, 27 of 27)

- [From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents](https://mlsanity.com/paper/2603.22386/) (2026)
- [Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems](https://mlsanity.com/paper/2603.01045/) (2026)
- [Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off](https://mlsanity.com/paper/2603.26815/) (2026)
- [HARBOR: Automated Harness Optimization](https://mlsanity.com/paper/2604.20938/) (2026)
- [Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions](https://mlsanity.com/paper/2604.07277/) (2026)
- [Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priors](https://mlsanity.com/paper/2604.25012/) (2026)
- [SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration](https://mlsanity.com/paper/2605.14089/) (2026)
- [ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration](https://mlsanity.com/paper/2605.20485/) (2026)
- [AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows](https://mlsanity.com/paper/2609.22951/) (2026)
- [Heterogeneous Scientific Foundation Model Collaboration](https://mlsanity.com/paper/2604.27351/) (2026)
- [Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generation](https://mlsanity.com/paper/2605.05657/) (2026)
- [LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning](https://mlsanity.com/paper/2605.14483/) (2026)
- [Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints](https://mlsanity.com/paper/2605.19140/) (2026)
- [Shared Prefixes, Better Credit: Adaptive Routing for Multi-Agent Reasoning](https://mlsanity.com/paper/2608.02291/) (2026)
- [FlowScout: From Execution Feedback to Reliable Tool-Using Agent Workflows](https://mlsanity.com/paper/2608.10039/) (2026)
- [n-Musketeers: Reinforcement Learning Shapes Collaboration Among Language Models](https://mlsanity.com/paper/2602.09173/) (2026)
- [OrchMAS: Orchestrated Reasoning with Multi Collaborative Heterogeneous Scientific Expert Structured Agents](https://mlsanity.com/paper/2603.03005/) (2026)
- [Compiling Deterministic Structure into SLM Harnesses](https://mlsanity.com/paper/2604.17450/) (2026)
- [FlowCompile: An Optimizing Compiler for Structured LLM Workflows](https://mlsanity.com/paper/2605.13647/) (2026)
- [Augment Engineering: A Methodology for Multi-Tool AI Orchestration Across Professional Domains](https://mlsanity.com/paper/2605.26146/) (2026)
- [When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Cost, and Task Difficulty](https://mlsanity.com/paper/2608.00685/) (2026)
- [EASy: Towards Efficient LLM-Based Agentic System](https://mlsanity.com/paper/2608.04588/) (2026)
- [Right-Sizing LLM-Agent Decomposition in VAT Determination: A Pilot Controlled Sweep](https://mlsanity.com/paper/2608.23395/) (2026)
- [AtomRec: Evolving Atomic Memory for Agentic Recommendation](https://mlsanity.com/paper/2609.04882/) (2026)
- [Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization](https://mlsanity.com/paper/2610.01017/) (2026)
- [CB-Orchestrator: Adaptive Workflow Optimization for LLM Agents via Contextual Bandits](https://mlsanity.com/paper/2610.13064/) (2026)
- [TurnCost: Turns, Not Observations: Cache-Aware Loop Engineering for Coding Agents](https://mlsanity.com/paper/2610.15093/) (2026)

## Abstract (arXiv)

Large Language Model (LLM)-based agentic systems have shown strong capabilities across various tasks. However, existing multi-agent 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 trade-offs 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 performance-aware 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.