mlsanityData to 14 Oct 2026

Traceable Knowledge Graph Reasoning Enables LLM-Assisted Decision Support for Industrial VOCs in the Steel Industry

arXiv 2605.27071 ↗First posted 26 May 2026cs.AIcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Key knowledge for steel-industry volatile organic compounds (VOCs) governance is scattered across unstructured scientific literature, making it difficult to integrate process, pollutant, and control-technology evidence and increasing the risk of hallucination when general large language models (LLMs) answer low-frequency industrial questions. Here we developed Chat-ISV, a knowledge graph (KG) enhanced multi-agent Q&A system that parses a curated steel-industry VOCs literature corpus, constructs a Neo4j KG with 27180 nodes and 81779 semantic edges, and combines prompt-constrained extraction, chunk-centered topology optimization, multi-agent routing, source-backtracking retrieval, local literature retrieval, open-domain knowledge access, and interactive subgraph visualization. Benchmark tests and 400 expert blind evaluations showed that topology optimization reduced isolated nodes from 57% to 4.08% and that Chat-ISV achieved high factual reliability, with 96.93% precision, 72.63% recall, an F1-score of 0.830, and a mean score of 1.69/2.00. By converting fragmented environmental-engineering literature into traceable, queryable, and decision-support-oriented knowledge, Chat-ISV establishes a scalable environmental-informatics paradigm for reliable LLM deployment and intelligent pollution-control decision support in specialized industrial domains.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 19 of its 51 references that are in the map. First posted on arXiv 26 May 2026.

Builds on

19 of 51 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  2. 2023LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities22 May

Other references · 17

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  5. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  6. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  7. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  8. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  9. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  10. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  11. 2020Knowledge Graphscited by 621
  12. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 333
5 more
  1. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 223
  2. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 152
  3. 2023LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplaycited by 63
  4. 2023Networked Multiagent Safe Reinforcement Learning for Low-carbon Demand Management in Distribution Networkcited by 4
  5. 2025Reshaping MOFs text mining with a dynamic multi-agents framework of large language modelcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Document Silos to Process Intelligence: A Multi-Layer Knowledge Graph for CMC Process Development
  2. 2025Knowledge Graph-Guided Multi-Agent Distillation for Reliable Industrial Question Answering with Datasets
  3. 2025IM-Chat: A Multi-agent LLM Framework Integrating Tool-Calling and Diffusion Modeling for Knowledge Transfer in Injection Molding Industry
  4. 2025A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy
  5. 2026A unified foundational framework for knowledge injection and evaluation of Large Language Models in Combustion Science
  6. 2025RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QA
  7. 2026GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design
  8. 2025FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes