When Evidence Shapes Collaboration: Knowledge-Conditioned Topology Generation for Multi-Agent Systems

• URL: http://arxiv.org/abs/2608.27984v2
• Date: Wed, 02 Sep 2026 10:56:17 GMT
• Title: When Evidence Shapes Collaboration: Knowledge-Conditioned Topology Generation for Multi-Agent Systems
• Abstract summary: We propose K-GAT (Knowledge-Guided Agent Topology Generator), a neuro-symbolic framework that formulates collaboration topology design as a knowledge-conditioned structure learning problem.<n>Experiments on knowledge-intensive benchmarks demonstrate K-GAT's efficiency and effectiveness.
• Score: 3.276908575835893
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-Agent Systems (MAS) have recently moved from static workflows toward dynamically generated collaboration topologies. However, existing topology generation methods rely primarily on the parametric knowledge of large language models, with external search or retrieval used only as a reactive tool rather than an explicit determinant of collaboration structure. This leads to structure-knowledge misalignment, where systems exhibit redundant interactions or insufficient verification in knowledge-intensive tasks. We propose K-GAT (Knowledge-Guided Agent Topology Generator), a neuro-symbolic framework that formulates collaboration topology design as a knowledge-conditioned structure learning problem, integrating external evidence directly into autoregressive graph generation. Extensive experiments on knowledge-intensive benchmarks demonstrate K-GAT's efficiency and effectiveness: notably on the expert-level GPQA dataset, K-GAT outperforms the LLM-Debate baseline by a substantial margin of +15.7% in accuracy, while consuming less than half the computational tokens.

Related papers

• Knowledge-Centric Agents for Workflow Generation [73.4340391112949]
  We propose a knowledge-centric framework that learns to invert, inject, and infer with knowledge across multiple abstraction levels.<n>Our method produces with richer node diversity, more coherent structures, and higher execution success rates than existing systems.
  arXiv  Detail & Related papers  (2026-07-17T11:03:01Z)
• Coupled Hierarchical Search over Topology and Execution for Agentic Workflow Synthesis [64.2820121997882]
  We introduce HierFlow, a training-free, test-time hierarchical search architecture that automates agentic workflow design.<n> HierFlow maximizes efficiency through an intelligent gating module that selectively triggers execution-level searches based on contextual necessity.<n> Comprehensive testing across question answering, mathematical reasoning, and code generation benchmarks confirms that HierFlow consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-05-20T01:56:11Z)
• Automatic Ontology Construction Using LLMs as an External Layer of Memory, Verification, and Planning for Hybrid Intelligent Systems [0.0]
  This paper presents a hybrid architecture for intelligent systems in which large language models (LLMs) are extended with an external ontological memory layer.<n>The proposed approach constructs and maintains a structured knowledge graph using RDF/OWL representations, enabling persistent, verifiable, and semantically grounded reasoning.
  arXiv  Detail & Related papers  (2026-04-22T17:19:43Z)
• Multi-hop Reasoning via Early Knowledge Alignment [68.28168992785896]
  Early Knowledge Alignment (EKA) aims to align Large Language Models with contextually relevant retrieved knowledge.<n>EKA significantly improves retrieval precision, reduces cascading errors, and enhances both performance and efficiency.<n>EKA proves effective as a versatile, training-free inference strategy that scales seamlessly to large models.
  arXiv  Detail & Related papers  (2025-12-23T08:14:44Z)
• SelfAI: Building a Self-Training AI System with LLM Agents [79.10991818561907]
  SelfAI is a general multi-agent platform that combines a User Agent for translating high-level research objectives into standardized experimental configurations.<n>An Experiment Manager orchestrates parallel, fault-tolerant training across heterogeneous hardware while maintaining a structured knowledge base for continuous feedback.<n>Across regression, computer vision, scientific computing, medical imaging, and drug discovery benchmarks, SelfAI consistently achieves strong performance and reduces redundant trials.
  arXiv  Detail & Related papers  (2025-11-29T09:18:39Z)
• Ontology Learning and Knowledge Graph Construction: A Comparison of Approaches and Their Impact on RAG Performance [0.0]
  This study investigates how different Knowledge Graph (KG) construction strategies influence RAG performance.<n>Ontology-guided KGs chunk information achieve competitive performance with state-of-the-art frameworks.
  arXiv  Detail & Related papers  (2025-11-08T12:38:45Z)
• Ontology-Enhanced Knowledge Graph Completion using Large Language Models [14.954155147351623]
  Large Language Models (LLMs) have been extensively adopted in Knowledge Graph Completion (KGC)<n>We propose an enhanced KGC method using LLMs -- OL-KGC.<n>It first leverages neural perceptual mechanisms to effectively embed structural information into the textual space, and then uses an automated extraction algorithm to retrieve ontological knowledge.
  arXiv  Detail & Related papers  (2025-07-28T09:00:48Z)
• Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems [58.95962217043371]
  We present a causal framework to analyze how agent outputs, whether correct or erroneous, propagate under topologies with varying sparsity.<n>Our empirical studies reveal that moderately sparse topologies, which effectively suppress error propagation while preserving beneficial information diffusion, typically achieve optimal task performance.<n>We propose a novel topology design approach, EIB-leanrner, that balances error suppression and beneficial information propagation by fusing connectivity patterns from both dense and sparse graphs.
  arXiv  Detail & Related papers  (2025-05-29T11:21:48Z)
• GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
  Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input.<n>GIVE guides the LLM agent to select the most pertinent expert data (observe), engage in query-specific divergent thinking (reflect), and then synthesize this information to produce the final output (speak)
  arXiv  Detail & Related papers  (2024-10-11T03:05:06Z)
• FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models [50.331708897857574]
  We introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications. FactorLLM achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed.
  arXiv  Detail & Related papers  (2024-08-15T16:45:16Z)

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.