# Decoupled Multi-Agent Orchestration

arXiv: https://arxiv.org/abs/2610.07556 · HTML: https://mlsanity.com/paper/2610.07556/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 56 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 29 of 29)

- [Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks](https://mlsanity.com/paper/2411.04468/) (2024)
- [Multi-agent Architecture Search via Agentic Supernet](https://mlsanity.com/paper/2502.04180/) (2025)
- [Towards a Science of Scaling Agent Systems](https://mlsanity.com/paper/2512.08296/) (2025)
- [G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks](https://mlsanity.com/paper/2410.11782/) (2024)
- [FlowReasoner: Reinforcing Query-Level Meta-Agents](https://mlsanity.com/paper/2504.15257/) (2025)
- [A Survey of Temporal Credit Assignment in Deep Reinforcement Learning](https://mlsanity.com/paper/2312.01072/) (2023)
- [CARROT: A Cost Aware Rate Optimal Router](https://mlsanity.com/paper/2502.03261/) (2025)
- [AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration](https://mlsanity.com/paper/2602.03786/) (2026)
- [LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing](https://mlsanity.com/paper/2502.02743/) (2025)
- [MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks](https://mlsanity.com/paper/2601.14652/) (2026)
- [Prompt-to-Leaderboard](https://mlsanity.com/paper/2502.14855/) (2025)
- [MAS-ZERO: Designing Multi-Agent Systems with Zero Supervision](https://mlsanity.com/paper/2505.14996/) (2025)
- [MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines](https://mlsanity.com/paper/2507.22606/) (2025)
- [AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation](https://mlsanity.com/paper/2602.17100/) (2026)
- [Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers](https://mlsanity.com/paper/2505.12601/) (2025)
- [MetaGen: Self-Evolving Roles and Topologies for Multi-Agent LLM Reasoning](https://mlsanity.com/paper/2601.19290/) (2026)
- [CARD: Towards Conditional Design of Multi-agent Topological Structures](https://mlsanity.com/paper/2603.01089/) (2026)
- [The Era of Agentic Organization: Learning to Organize with Language Models](https://mlsanity.com/paper/2510.26658/) (2025)
- [Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation](https://mlsanity.com/paper/2605.05007/) (2026)
- [Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systems](https://mlsanity.com/paper/2603.21475/) (2026)
- [Asynchronous Credit Assignment for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2408.03692/) (2024)
- [Multi-level Advantage Credit Assignment for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2508.06836/) (2025)
- [MAS-on-the-Fly: In-Context Structural Adaptation of LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2602.13671/) (2026)
- [Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning](https://mlsanity.com/paper/2604.00344/) (2026)
- [Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts](https://mlsanity.com/paper/2604.00901/) (2026)
- [ORI: O Routing Intelligence](https://mlsanity.com/paper/2502.10051/) (2025)
- [Multi-Agent Coordination Adaptation via Structure-Guided Orchestration](https://mlsanity.com/paper/2605.25746/) (2026)
- [EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems](https://mlsanity.com/paper/2605.08769/) (2026)
- [LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning](https://mlsanity.com/paper/2605.14483/) (2026)

## Abstract (arXiv)

Learned orchestration can automatically construct effective language-model multi-agent systems, but existing approaches couple planning to fixed worker pools and train decomposition and collaboration from the same terminal outcome, limiting transfer and obscuring credit assignment. We introduce DeOrch, which separates worker-agnostic planning from concrete worker selection. Its two-stage planner first decomposes the task without worker information, then chooses collaboration operations using compact, worker-identity-free matchability feedback from the pool, enabling conditional credit assignment to decomposition and collaboration decisions. A lightweight matcher estimates worker suitability from behavior on a fixed probe set and adapts online with a contextual bandit, allowing new workers to be incorporated without retraining the planner or matcher. Across diverse in- and out-of-distribution tasks, DeOrch outperforms prior automatic MAS orchestration methods with fewer worker calls than competing learned orchestrators, remains effective when transferred to an entirely unseen worker pool without retraining, and shows consistent gains from both components.