Multi-Agent Coordination Adaptation via Structure-Guided Orchestration

• URL: http://arxiv.org/abs/2605.25746v1
• Date: Mon, 25 May 2026 11:59:58 GMT
• Title: Multi-Agent Coordination Adaptation via Structure-Guided Orchestration
• Abstract summary: We introduce MACA, an automated coordination framework that learns a task- and budget-conditioned structural prior over agent participation and interactions.<n>Across benchmarks, MACA outperforms adaptive multi-agent baselines by an average of 8.42% while using 43.19% fewer tokens.<n>Further investigation reveals that joint adaptation of structure and orchestrations suppresses redundant interactions, converging coordination toward task-effective execution.
• Score: 5.230083115652549
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As large language model (LLM)-based multi-agent systems scale to handle increasingly complex tasks, balancing structural stability and dynamic adaptability becomes increasingly challenging. Existing systems typically adopt either structure-centric methods, committing to structures determined upfront that limit fine-grained control, or orchestration-centric methods, adapting decisions dynamically while leaving coordination structure implicit and unstable. To address this challenge, we revisit multi-agent coordination from a probabilistic perspective, casting it as posterior inference over the joint distribution of structure and orchestration. We introduce MACA, an automated coordination framework that learns a task- and budget-conditioned structural prior over agent participation and interactions. This prior guides a policy-based orchestration as an approximation to posterior inference, enabling efficient solutions with fine-grained control. Across benchmarks, MACA outperforms adaptive multi-agent baselines by an average of 8.42% while using 43.19% fewer tokens. Further investigation reveals that joint adaptation of structure and orchestration suppresses redundant interactions, converging coordination toward task-effective execution.

Related papers

• Orchestra-o1: Omnimodal Agent Orchestration [72.34907006336108]
  Orchestra-o1 is an omnimodal agent orchestration framework designed to support efficient agent collaboration across multiple modalities.<n>This work introduces a unified orchestration mechanism that enables modality-aware task decomposition, online sub-agent specialization, and parallel sub-task execution.<n>This scalable design allows agent systems to effectively tackle complex real-world tasks involving heterogeneous information sources, surpassing the second-best approach by 10.3% accuracy on the OmniGAIA benchmark.
  arXiv  Detail & Related papers  (2026-06-10T04:50:35Z)
• When Does Hierarchy Help? Benchmarking Agent Coordination in Event-Driven Industrial Scheduling [7.912877527497326]
  DESBench is a benchmark for evaluating agent coordination in hierarchical event-driven scheduling.<n>We focus on four representative coordination paradigms: centralized, hierarchical, heterarchical, and holonic.
  arXiv  Detail & Related papers  (2026-05-13T08:33:28Z)
• Small Model as Master Orchestrator: Learning Unified Agent-Tool Orchestration with Parallel Subtask Decomposition [61.291733522717415]
  Agent-as-Tool is a unified parallel orchestration paradigm that mitigates both agents and tools into a standardized, learnable action space.<n>ParaManager decouples planning decisions from subtask solving, enabling state-aware parallel subtask decomposition, delegation, and asynchronous execution.<n>Experiments show that ParaManager achieves strong performance across multiple benchmarks and exhibits robust generalization under unseen model pools.
  arXiv  Detail & Related papers  (2026-04-18T14:41:27Z)
• Chain of Modality: From Static Fusion to Dynamic Orchestration in Omni-MLLMs [84.3271821505699]
  Chain of Modality (CoM) is an agentic framework that transitions multimodal fusion from passive concatenation to dynamic orchestration.<n> operating in either a training-free or a data-efficient SFT setting, CoM achieves robust and consistent generalization across diverse benchmarks.
  arXiv  Detail & Related papers  (2026-04-16T01:21:14Z)
• Decision-Theoretic Safety Assessment of Persona-Driven Multi-Agent Systems in O-RAN [0.2873445316250935]
  We introduce a persona driven multi agent framework for autonomous network management.<n>We evaluate 486 persona configurations across two ORAN optimization challenges.<n>Results demonstrate that persona agent alignment significantly impacts both individual performance and emergent multi agent coordination.
  arXiv  Detail & Related papers  (2026-04-03T15:20:16Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• Hierarchical Adaptive Consensus Network: A Dynamic Framework for Scalable Consensus in Collaborative Multi-Agent AI Systems [0.5505634045241287]
  This article introduces a three-tier architecture for consensus strategies in multi-agent systems.<n>The first layer collects the confidence-based voting outcomes of several local agent clusters.<n>The second level facilitates inter-cluster communication through cross-clustered partial knowledge sharing and dynamic timeouts.<n>The third layer provides system-wide coordination and final arbitration by employing a global orchestration framework.
  arXiv  Detail & Related papers  (2025-11-16T15:09:15Z)
• Deep Reinforcement Learning for Multi-Agent Coordination [8.250169938213558]
  We propose a Stigmergic Multi-Agent Deep Reinforcement Learning (S-MADRL) framework that leverages virtual pheromones to model local and social interactions.<n>We show that our framework achieves the most effective coordination of up to eight agents, where robots self-organize into asymmetric workload distributions.<n>This emergent behavior, analogous to strategies observed in nature, demonstrates a scalable solution for decentralized multi-agent coordination in crowded environments.
  arXiv  Detail & Related papers  (2025-10-04T00:47:20Z)
• AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction [77.62279834617475]
  We propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure.<n>Our method focuses on two key directions: (1) Next-Agent Prediction, which selects the most suitable agent role at each step, and (2) Next-Context Selection, which enables each agent to selectively access relevant information from any previous step.
  arXiv  Detail & Related papers  (2025-06-21T18:34:43Z)
• Multi-Agent Collaboration via Evolving Orchestration [55.574417128944226]
  Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-solving.<n>We propose a puppeteer-style paradigm for LLM-based multi-agent collaboration, where a centralized orchestrator ("puppeteer") dynamically directs agents ("puppets") in response to evolving task states.<n> Experiments on closed- and open-domain scenarios show that this method achieves superior performance with reduced computational costs.
  arXiv  Detail & Related papers  (2025-05-26T07:02:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.