Dynamic Coordination Strategy Selection for Enterprise Multi-Agent Systems

• URL: http://arxiv.org/abs/2606.00804v2
• Date: Thu, 04 Jun 2026 11:06:01 GMT
• Title: Dynamic Coordination Strategy Selection for Enterprise Multi-Agent Systems
• Abstract summary: This paper evaluates whether coordination strategy should be selected dynamically by problem class rather than fixed globally.<n>All 1,440 generated outputs are judged by a fixed Sonnet rubric.<n>We conclude that enterprise coordination policy should use dynamic routing as a default, not as a deterministic winner-selection law.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Enterprise multi-agent systems increasingly expose multiple coordination patterns, but deployments often lack evidence for when to use consensus, debate, synthesis, or a simpler single-agent workflow. This paper evaluates whether coordination strategy should be selected dynamically by problem class rather than fixed globally. We run a frozen matrix of 30 enterprise tasks spanning six industries, five problem classes, four execution conditions, three replications per cell, and four model arms: qwen_local, sonnet, gemma_openrouter, and an auxiliary openai cloud-validation arm. All 1,440 generated outputs are judged by a fixed Sonnet rubric. The main finding is bounded and operationally useful, but it is not the original strict H1. The pre-registered exact-winner/CI criterion is not supported: exact winner identity is unstable across model arms, and several predicted strategies are close to, but not above, the best observed alternative. A weaker near-best routing claim is strongly supported. In every pre-registered model arm and problem class, and again in the auxiliary OpenAI validation arm, the predicted strategy is within 0.10 quality-score points of the best observed condition. Structured compliance verification is the clearest exception to the original mapping: all arms favor single_agent rather than consensus. A pre-registered Kendall's W test finds no reliable difference between Vietnamese-domain and English-domain tasks in how consistently the four coordination conditions are ranked (mean W of 0.20 in both strata; signed-rank p = .85), so H2 is not supported. We conclude that enterprise coordination policy should use dynamic routing as a calibrated default, not as a deterministic winner-selection law.

Related papers

• Right-Sizing LLM-Agent Decomposition in VAT Determination: A Pilot Controlled Sweep [0.3384279376065155]
  This pilot studies that choice on bounded cross-border VAT determination with reverse charge.<n>We hold the activity surface fixed (subtasks, tools, I/O schemas, validation checks, orchestrator, base model, and merge policy)<n>The program spans 4,400 runs: a 40-case, five-repeat main sweep, matched-token arms separating prompt-budget from agent-count effects, and three failure-injection arms.
  arXiv  Detail & Related papers  (2026-08-24T15:40:15Z)
• Making two action heads agree: coordination mechanisms and a runtime collapse certificate for flow-matching policies [13.05465000489116]
  Flow-matching policy decodes each predicted motion into joint and end-effector spaces.<n>On multimodal tasks, independently sampled branches may choose different valid modes, causing false alarms.<n>We study how to coordinate the two branches and at what cost.
  arXiv  Detail & Related papers  (2026-08-16T13:57:36Z)
• PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity [0.24554686192257422]
  PoTRE (Poly-Topological Reasoning Ensembles) is a heterogeneous framework that decouples inference into four agents.<n>We evaluate PoTRE on three frontier benchmarks: ARC-AGI-2, Humanity's Last Exam (HLE), and PRBench Finance.<n>PoTRE achieves state-of-the-art accuracy of 49.92% on HLE, surpassing the previous best official score.
  arXiv  Detail & Related papers  (2026-07-22T15:20:53Z)
• ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents [61.184954205350984]
  ClawArena-Team is a benchmark of 41 multi-turn, multimodal, multi-agent scenarios spanning 258 evaluation rounds and 72 staged updates.<n>All scoring is execution-based with no LLM judge: an overall score -- the Subagent-Management Score (SMS) -- multiplies task correctness by a least-privilege and modality-routing factor.
  arXiv  Detail & Related papers  (2026-06-30T06:06:08Z)
• KYA: A Framework-Agnostic Trust Layer for Autonomous Systems with Verifiable Provenance and Hierarchical Policy Composition [0.0]
  KYA (Know Your Agents) is an open-source, framework-agnostic trust and governance layer for autonomous systems.<n>It is available under Apache 2.0 as the veldt-kya package on PyPI.
  arXiv  Detail & Related papers  (2026-05-25T02:59:54Z)
• An Interpretable CF-RL-TOPSIS Fusion Model for Skills-Aware Talent Recommendation [0.0]
  This study proposes an interpretable late-fusion model that integrates a transition-aware collaborative branch, a reinforcement-style occupation-family bandit, and an entropy-weighted TOPSIS branch constructed from six semantic proxies.<n>The model is evaluated on two frozen public ICT talent-history benchmarks, JobHop and Karrierewege, using repeated chronological top-5 ranking and paired Wilcoxon tests.
  arXiv  Detail & Related papers  (2026-05-22T19:22:58Z)
• Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems [0.0]
  Multi-agent LLM systems fail in production at rates between 41% and 87%, mostly due to coordination defects.<n>We argue that coordination should be treated as a architectural layer, separable from agent logic and from information access.<n>We instantiate this with an information-controlled design on prediction markets.
  arXiv  Detail & Related papers  (2026-05-05T02:56:44Z)
• 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)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• SemiReward: A General Reward Model for Semi-supervised Learning [58.47299780978101]
  Semi-supervised learning (SSL) has witnessed great progress with various improvements in the self-training framework with pseudo labeling. Main challenge is how to distinguish high-quality pseudo labels against the confirmation bias. We propose a Semi-supervised Reward framework (SemiReward) that predicts reward scores to evaluate and filter out high-quality pseudo labels.
  arXiv  Detail & Related papers  (2023-10-04T17:56:41Z)
• Pure Exploration under Mediators' Feedback [63.56002444692792]
  Multi-armed bandits are a sequential-decision-making framework, where, at each interaction step, the learner selects an arm and observes a reward. We consider the scenario in which the learner has access to a set of mediators, each of which selects the arms on the agent's behalf according to a and possibly unknown policy. We propose a sequential decision-making strategy for discovering the best arm under the assumption that the mediators' policies are known to the learner.
  arXiv  Detail & Related papers  (2023-08-29T18:18:21Z)
• Optimal Clustering with Bandit Feedback [57.672609011609886]
  This paper considers the problem of online clustering with bandit feedback. It includes a novel stopping rule for sequential testing that circumvents the need to solve any NP-hard weighted clustering problem as its subroutines. We show through extensive simulations on synthetic and real-world datasets that BOC's performance matches the lower boundally, and significantly outperforms a non-adaptive baseline algorithm.
  arXiv  Detail & Related papers  (2022-02-09T06:05:05Z)

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.