Recent advances in Large Language Models (LLMs) and autonomous AI agents are rapidly transforming intelligent systems, networked applications, and decision-making infrastructures. Meanwhile, graph intelligence has emerged as a fundamental paradigm for modeling structured relationships, long-range dependencies, relational reasoning, and interpretable knowledge organization. The integration of graph intelligence with LLMs and autonomous agents is enabling a new generation of intelligent systems capable of memory augmentation, multi-hop reasoning, planning, coordination, and adaptive interaction in complex environments. Emerging paradigms such as GraphRAG, graph-based agent memory, multi-agent coordination graphs, and graph-guided reasoning are attracting growing attention from both academia and industry.

However, despite rapid progress, critical challenges remain regarding robustness, reliability, safety, interpretability, alignment, and trustworthy deployment. Graph-enhanced intelligent systems are vulnerable to adversarial attacks, memory poisoning, hallucination propagation, unreliable retrieval, unsafe planning, and multi-agent coordination failures. Ensuring trustworthy graph intelligence has therefore become a key requirement for deploying LLMs and autonomous agents in real-world applications involving cybersecurity, healthcare, finance, recommendation systems, scientific discovery, and intelligent infrastructure.

This Call for Paper (CFP) aims to provide a high-quality interdisciplinary forum for researchers and practitioners working at the intersection of graph intelligence, large language models, autonomous agents, and trustworthy AI. The issue will focus on foundational theories, algorithms, architectures, systems, evaluation methodologies, and real-world applications for trustworthy graph-enhanced intelligent systems.

Topics of Interest

Topics include, but are not limited to:

1. Graph-Enhanced LLMs and GraphRAG

• Graph foundation models
• Graph-enhanced large language models
• Knowledge graph augmented LLMs
• Graph Retrieval-Augmented Generation (GraphRAG)
• Hybrid graph-vector retrieval
• Multi-hop graph reasoning
• Structured memory augmentation
• Dynamic and temporal graph retrieval
• Graph-guided prompting and reasoning

2. Autonomous and Multi-Agent Systems

• Graph-based autonomous agents
• Agent memory graphs
• Planning and reasoning over graphs
• Multi-agent graph intelligence
• Communication and coordination graphs
• Collaborative agent reasoning
• Workflow and tool dependency graphs
• Long-horizon autonomous decision making
• Distributed agent systems

3. Trustworthy and Safe AI Systems

• Trustworthy graph intelligence
• Safety alignment for graph-enhanced agents
• Robust graph reasoning
• Hallucination mitigation via graph structures
• Safe retrieval and grounded generation
• Human-in-the-loop graph agents
• Trust calibration and reliability assessment
• Responsible and ethical graph AI

4. Adversarial Robustness and Security

• Adversarial attacks on graph-enhanced LLMs
• Graph poisoning and backdoor attacks
• Prompt injection through graph memory
• Multi-agent adversarial collaboration
• Secure graph retrieval systems
• Defensive architectures for graph agents
• Privacy-preserving graph intelligence
• Trust management in autonomous systems

5. Explainability, Verification, and Evaluation

• Explainable graph reasoning
• Interpretable GraphRAG systems
• Causal graph intelligence
• Formal verification for graph-agent systems
• Certified robustness and reliability
• Benchmarking trustworthy graph AI
• Evaluation frameworks for autonomous agents
• Reasoning trace analysis

6. Systems and Applications

• Scalable graph-agent infrastructures
• Real-time graph intelligence systems
• Efficient graph memory architectures
• Scientific discovery agents
• Recommendation and personalization
• Cybersecurity and fraud detection
• Healthcare and biomedical applications
• Financial network intelligence
• Industrial and IoT applications

Types of Submissions

We welcome original and high-quality contributions in the following categories:

• Original research papers
• Survey and review articles
• System and benchmark papers
• Application and industrial papers

Academic Editors

Prof. Xixun Lin (linxixun@iie.ac.cn), Institute of Information Engineering, Chinese Academy of Sciences, China.
Dr. He Zhang (h.zhang@griffith.edu.au), Griffith University, Australia.
Prof. Pengfei Cao (pengfei.cao@nlpr.ia.ac.cn), Institute of Automation, Chinese Academy of Sciences, China.
Prof. Lixin Zou (zoulixin@whu.edu.cn), Wuhan University, China.
Prof. Henry Nguyen (h.zhang@griffith.edu.au ), Griffith University, Australia.

Submission Guidelines

To submit your manuscript, please go to the Transactions on Graph Intelligence and Network Applications journal website at Add Submissions - Scilight Press and follow the procedures for manuscript submission. Author Submission Guidelines can be found at: Instruction for Authors - | Transactions on Graph Intelligence and Network Applications. Please make sure to include the title of this Call for Papers in the cover letter.

There is no Article Processing Charge for all submissions and accepted papers.

Important Dates

All deadlines are end-of-day in the Anywhere on Earth (AoE) time zone. All accepted papers will be published in the earliest available issue. The above timeline is provided for reference only, and the actual schedule may be subject to change.

All manuscripts will be peer-reviewed following the established policies and procedures of the journal. The final papers will be selected for publication depending on the results of the peer-review process and the reviews of the Academic Editors and Editor-in-Chief.