Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems

• URL: http://arxiv.org/abs/2605.03310v1
• Date: Tue, 05 May 2026 02:56:44 GMT
• Title: Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems
• Abstract summary: 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.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent LLM systems fail in production at rates between 41% and 87%, mostly due to coordination defects rather than base-model capability. Existing responses split between cataloguing failure modes empirically and shipping declarative orchestration frameworks as engineering tools; neither delivers a principled mapping from coordination configuration to predictable failure-mode signature. We argue that coordination should be treated as a configurable architectural layer, separable from agent logic and from information access, enabling architectural reasoning rather than only engineering productivity. We instantiate this with an information-controlled design on prediction markets: a single LLM, fixed tools, fixed per-call output cap, and fixed prompt template across five reference coordination configurations, with total compute per question treated as an endogenous architectural output. The Murphy decomposition of the Brier score separates calibration from discriminative power, so configurations leave distinguishable signatures even when aggregate scores coincide. On 100 Polymarket binary markets resolved after the model's training cutoff (claude-opus-4-6) we report Murphy signatures, a cost-quality Pareto frontier, category-conditioned analysis, and a bootstrap power-projection. Three of five pre-specified predictions are upheld in direction; two configurations dominate the Pareto frontier within this regime; exploratory bootstrap intervals separate consensus alignment from others, though pairwise tests do not survive Bonferroni correction at n=100. We also deploy the same configurations as live agents on Foresight Arena under web-search-enabled conditions, as an on-chain replication channel accumulating in parallel. Harness, trace dataset, and production agents are released. We position this as a methodology-validating first instantiation, not a general cross-model claim.

Related papers

• Automated Hardware Validation Test Plan Generation for Large Scale AI Datacenter Platforms Using a Generative AI Multi-Agents Architecture [4.668322408437681]
  This paper presents a generative AI multi-agent architecture that automates the generation of structured hardware validation test plans.<n> evaluated on two production platforms against manual baselines, the framework achieves coverage expansions of 74.2% and 51.4%, cutting authoring from days to hours.
  arXiv  Detail & Related papers  (2026-07-17T17:41:33Z)
• Gatekeepers and Hallucinations: A Layered Evaluation Framework for LLM-Driven Quantum Circuit Generation [0.0]
  We present a layered evaluation framework for materials-informed Variational Quantum Eigensolver (VQE) circuit generation.<n>We surface a taxonomy of five distinct LLM failure modes (geometry hallucination, nonexistent API usage, integration failures, constraint violations, and plausible-but-unverifiable output)<n>A forensic audit of the evaluation platform's own source code further establishes that two apparent model failures originated in the harness through silent fallback-template substitution.
  arXiv  Detail & Related papers  (2026-06-16T19:17:54Z)
• Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers [72.66457738838515]
  We propose a Transformer-based Fixed-Point Reasoning Model that uses fixed-point convergence as an end-to-end halting mechanism in a looped architecture.<n>FPRM is effective on common reasoning benchmarks, namely Sudoku, Maze, state-tracking, and ARC-AGI.
  arXiv  Detail & Related papers  (2026-06-16T17:36:33Z)
• A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents [0.0]
  This paper names that boundary thedeterministic boundary (SDB): a four-part contract among a proposer, verifier, commit step, and reject signal.<n>We argue that the SDB is the load-bearing primitive of production agent runtimes.<n>We present a catalog of six runtime patterns that compose the SDB differently across conversational, autonomous, and long-horizon agents.
  arXiv  Detail & Related papers  (2026-05-19T17:54:21Z)
• CellScientist: Dual-Space Hierarchical Orchestration for Closed-Loop Refinement of Virtual Cell Models [62.281480231694]
  Virtual Cell Modeling (VCM) requires models that not only predict perturbation responses, but also support targeted revision when predictions fail.<n>Current LLM-assisted modeling face a refinement-routing problem: prediction discrepancies are observed through executable implementations.<n>We propose CellScientist, a dual-space hierarchical framework that couples a high-level hypothesis space with a low-level executable implementation space.
  arXiv  Detail & Related papers  (2026-05-08T06:40:24Z)
• Towards Multi-Agent Autonomous Reasoning in Hydrodynamics [0.06999740786886537]
  We present a multi-agent system (MAS) prototype for hydrodynamics in which specialized agents are coordinated through a Layer Execution Graph (LEG)<n>A planner agent constructs query-specific execution topologies from natural-language routings that capture domain knowledge without hard-coding it as rigid control logic.<n>A reporter agent synthesizes the final response, while the runtime logs provenance for every tool invocation to support auditability.
  arXiv  Detail & Related papers  (2026-05-01T21:17:55Z)
• Decision Trace Schema for Governance Evidence in Real-Time Risk Systems [0.0]
  No single logging format captures the complete governance-relevant record of how a decision was reached.<n>DES defines ten required root-level fields and introduces a tiered evidence strategy.<n> DES is the only specification covering all four layers simultaneously.
  arXiv  Detail & Related papers  (2026-04-10T13:06:38Z)
• Auto-Configured Networks for Multi-Scale Multi-Output Time-Series Forecasting [7.883762084227456]
  Industrial forecasting often involves multi-source asynchronous signals and multi-output targets.<n>Current practices fix alignment strategies or network designs, making it difficult to systematically co-design preprocessing.<n>We propose an auto-configuration framework that outputs a deployable Pareto set of forecasting models balancing error and complexity.
  arXiv  Detail & Related papers  (2026-04-08T21:28:30Z)
• MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale [92.09717763663873]
  We present MinerU2.5-Pro, which advances the state of the art purely through data engineering and training strategy design.<n>At its core is a Data Engine co-designed around coverage, informativeness, and annotation accuracy.<n>We show that MinerU2.5-Pro achieves 95.69 on OmniDocBench v1.6, improving over the same-architecture baseline by 2.71 points and surpassing all existing methods.
  arXiv  Detail & Related papers  (2026-04-06T15:44:18Z)
• Automated Self-Testing as a Quality Gate: Evidence-Driven Release Management for LLM Applications [51.56484100374058]
  We present an automated self-testing framework that introduces quality gates with evidence-based release decisions.<n>We evaluate the framework through a longitudinal case study of an internally deployed multi-agent conversational AI system.
  arXiv  Detail & Related papers  (2026-03-13T20:44:15Z)
• ORCH: many analyses, one merge-a deterministic multi-agent orchestrator for discrete-choice reasoning with EMA-guided routing [0.6445605125467574]
  ORCH is a framework for discrete-choice reasoning that orchestrates heterogeneous language models.<n>It uses fixed rules for task decomposition and answer aggregation, keeping the pipeline predictable, reproducible, and training-free.<n>Experiments on MMLU, MMLU-Pro, and GSM8K show that ORCH consistently outperforms single-model baselines and a majority-vote ensemble.
  arXiv  Detail & Related papers  (2026-02-02T08:27:58Z)
• 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)
• Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction [58.51530390018909]
  Large Language Model based multi-agent systems excel at collaborative problem solving but remain brittle to cascading errors.<n>We present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction.
  arXiv  Detail & Related papers  (2025-10-16T05:35:37Z)
• Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty [49.19257648205146]
  We propose an unsupervised conformal inference framework for generation.<n>Our gates achieve close-to-nominal coverage and provide tighter, more stable thresholds than split UCP.<n>The result is a label-free, API-compatible gate for test-time filtering.
  arXiv  Detail & Related papers  (2025-09-26T23:40:47Z)

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.