Knowledge Graph-Guided Multi-Agent Distillation for Reliable Industrial Question Answering with Datasets

2025-10-03 · Jiqun Pan, Zhenke Duan, Jiani Tu, Anzhi Cheng, Yanqing Wang arxiv

Industrial question-answering (QA) systems require higher safety and reliability than general-purpose dialogue models, as errors in high-risk scenarios such as equipment fault diagnosis can have severe consequences. Although multi-agent large language models enhance reasoning depth, they suffer from uncontrolled iterations and unverifiable outputs, and conventional distillation methods struggle to transfer collaborative reasoning capabilities to lightweight, deployable student models. To address these challenges, we propose Knowledge Graph-guided Multi-Agent System Distillation (KG-MASD). Our approach formulates distillation as a Markov Decision Process and incorporates a knowledge graph as a verifiable structured prior to enrich state representation and ensure convergence. By integrating collaborative reasoning with knowledge grounding, KG-MASD generates high-confidence instruction-tuning data and jointly distills reasoning depth and verifiability into compact student models suitable for edge deployment. Experiments on an industrial QA dataset show that KG-MASD improves accuracy by 2.4 per cent to 20.1 per cent over baselines and significantly enhances reliability, enabling trustworthy AI deployment in safety-critical industrial scenarios. Code and data are available at https://github.com/erwinmsmith/KG-MAD/.

📄 PDF Abstract BibTeX arXiv:2510.06240

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering Fault Diagnosis

InfGraND: An Influence-Guided GNN-to-MLP Knowledge Distillation

2026-01-12 · Amir Eskandari, Aman Anand, Elyas Rashno, Farhana Zulkernine arxiv

Graph Neural Networks (GNNs) are the go-to model for graph data analysis. However, GNNs rely on two key operations - aggregation and update, which can pose challenges for low-latency inference tasks or resource-constrain…

Knowledge Distillation

Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPs

2023-03-24 · Taiqiang Wu, Zhe Zhao, Jiahao Wang, Xingyu Bai 외

Distilling high-accuracy Graph Neural Networks (GNNs) to low-latency multilayer perceptions (MLPs) on graph tasks has become a hot research topic. However, conventional MLP learning relies almost exclusively on graph nod…

Knowledge Distillation

Knowledge Distillation from Language-Oriented to Emergent Communication for Multi-Agent Remote Control

2024-01-23 · Yongjun Kim, Sejin Seo, Jihong Park, Mehdi Bennis 외

In this work, we compare emergent communication (EC) built upon multi-agent deep reinforcement learning (MADRL) and language-oriented semantic communication (LSC) empowered by a pre-trained large language model (LLM) usi…

Deep Reinforcement Learning Knowledge Distillation Language Modeling Language Modelling+2

m-KAILIN: Knowledge-Driven Agentic Scientific Corpus Distillation Framework for Biomedical Large Language Models Training

2025-04-28 · Meng Xiao, Xunxin Cai, Qingqing Long, Chengrui Wang 외

Corpus distillation for biomedical large language models (LLMs) seeks to address the pressing challenge of insufficient quantity and quality in open-source annotated scientific corpora, which remains a bottleneck for eff…

Question Answering

LLM-Guided Knowledge Distillation for Temporal Knowledge Graph Reasoning

2026-02-16 · Wang Xing, Wei Song, Siyu Lin, Chen Wu 외 arxiv

Temporal knowledge graphs (TKGs) support reasoning over time-evolving facts, yet state-of-the-art models are often computationally heavy and costly to deploy. Existing compression and distillation techniques are largely …

Knowledge Distillation Knowledge Graphs Link Prediction