NORA'26 - Workshop on Knowledge Graphs & Agentic Systems Interplay

Agents have experienced significant growth in recent years, largely due to the rapid technological advancements of Large Language Models (LLMs). Although these agents benefit from LLMs’ advanced generation proficiency, they still suffer from catastrophic forgetting and a limited context window size compared to the agents’ needs in terms of contextual information. Knowledge Graphs (KGs) are a powerful paradigm for structuring and managing connected pieces of information while unlocking deeper insights than traditional methods. Their value is immense for tasks that require context, integration, inter-linking, and reasoning. However, this power comes at the cost of significant upfront and ongoing investment in construction, curation, and specialised expertise. The NORA workshop aims at analysing and discussing emerging and novel practices, ongoing research efforts and validated or deployed innovative solutions that showcase the growing synergy between LLMs agents and KGs.

The recent proliferation of large language models (LLMs) has opened the doors for new paradigms that benefit many applications like intelligent assistants, content creation & summarisation, code generation & debugging, and knowledge discovery, to name a few. Such applications are achieved through prompt engineering & in-context learning, retrieval augmented generation, fine-tuning & alignment, and function calling & tool usage. These families of techniques can be used on their own or combined for better results.

Thanks to the constantly improving reasoning and function calling capabilities of LLMs, LLM-based agents have attracted more attention. While performing their allocated tasks, these agents usually need to accumulate memory and feedbacks from tool calls and maintain a long run of these tasks. Consequently, they can easily exceed the context window size, explode costs, and degrade both latency and performance, due to their growing usage of tokens.

Depending on their tasks, agents usually need access to minimal portions of semantic memory (i.e. facts), episodic memory (i.e. events), and procedural memory (i.e. instructions). However, it remains challenging for agents to select relevant examples from different memories, especially in large-scale applications (e.g., personal memories for personal assistance).

Knowledge Graphs (KGs) model data and knowledge in a structured and explicit format known as graphs. Thanks to this native structure, they have demonstrated great capabilities in capturing rich semantics and connections between entities and concepts in both closed and open domains. This feature has enabled both 1) complex logical reasoning, which is needed for multi-hop queries and deriving new implicit knowledge from explicit facts; and 2) graph-based learning through richer features of the structured data. However, curating knowledge can be challenging, especially from heterogeneous data sources and formats (e.g., personal assistants). As a consequence, large-scale and industrial applications' scenarios are even more impacted by this bottleneck, which thereby lower the adoption of pure KG-based solutions in some Industrial use-cases.

Therefore, this first edition of the workshop aims to unveil the emerging yet growing interplay between two key paradigms of recent AI systems: Agents and Knowledge Graphs. On the one hand, the efficiency and performance of agentic systems can benefit greatly from KGs as a structured data model and reasoning foundation, especially in designing and implementing their various memories. On the other hand, KGs can leverage the advanced linguistic capabilities of LLM agents in extracting, computing and engineering knowledge from unstructured, multi-modal & multi-lingual data sources.

Topics of interest include, but are not limited to:

• gentic and Knowledgeable Systems with Small Language Models
• Agentic Information Extraction and Retrieval
• Agentic KG Construction & Enrichment
• Agents for Complex Reasoning over KGs
• Agents and KGs for private and proactive personal assistants & Personalisation
• Augmenting Agents with External Knowledge
• Collaborative Agents for Knowledge Computing and Serving
• Context Engineering enhanced by KGs
• Efficient Reinforcement Learning for better performance
• Graph Retrieval Augmented Generation in Agentic systems
• KGs serving agents’ memories: episodic (experiences, events, etc.), semantic (facts, concepts, etc.), and procedural (skills, tasks, etc.)
• Multi-Lingual & Multi-modal integrations
• On-Device or Hybrid (Device-Cloud) systems combining Agents and KGs
• Personalisation via Agents and KGs
• Personas and digital twins enabled by Agents and KGs
• Theoretical and experimental analysis of close and open Domain applications scenarios

We envision four types of submissions covering the entire workshop topics spectrum (page limits does not include references and appendices):

1. Research Papers (max 8 pages), presenting novel scientific research addressing topics of the workshop.
2. Position & Demo papers (max 6 pages), encouraging papers describing significant work in progress, late breaking results or ideas of the domain, as well as functional systems relevant to the community.
3. Industry & Use Case Presentations (max 6 pages), in which industry experts can present and discuss practical solutions, use case prototypes, best practices, etc. at any stage of implementation.
4. Tiny/Short Papers (max 2 pages), presenting research topics, works in progress, and practical applications

In order to ease the reviewing process, authors may add the track they are submitting to directly in their titles, for instance: "Article Title [Industry]".

Workshop submissions must be self-contained and in English. Note: The review process is double-blind, authors should be careful and submit anonymous articles.

All papers should be submitted to https://openreview.net/TO-BE-DEFINED.

• Abstract: January 15^th, 2026
• Submission: January 22^nd, 2026
• Notification: February 28^th, 2026
• Camera-ready: February 19^th, 2026
• Presentation: April XX^th, 2026

To be announced

Organisers

• Btissam Er-Rahmadi (Huawei Technologies R&D UK Ltd.) is a Senior Scientist at the Knowledge Graph Lab. She has been developing innovative and novel solutions designed for Knowledge Computing and Serving in many application scenarios belonging to different domains (e.g., personal assistants, e-commerce, geospatial search, etc.). She also has experience in applying operations research methods, mainly mathematical optimisation and simulations, to enhance the performance of distributed systems. She is interested in leveraging Deep Learning and NLP with knowledge engineering to construct advanced, seamless and practical approaches. Previously, she has organized the first N2Women Meet- ing at WiMob 2015 in UAE.
• Damien Graux (EcoVadis) leads a team of research scientists at EvoVadis that is specialised in AI/ML. He has been contributing to research efforts in Knowledge Computing technologies: focusing inter alia on Semantic Web, designing complex pipelines for heterogeneous Big Data and LLM-based knowledge management. Prior to this, he had research positions at Huawei R&D (UK), at Inria (France), Trinity College Dublin (Ireland) and Fraunhofer IAIS (Germany). He has been involved in the organisations of many international workshops at major conferences such as the LASCAR (co-located with ESWC) or the MEPDaW (co-located with ISWC) series, and more recently PromptEng (co-located with the ACM WebConf).
• Sebastien Montella (Huawei Technologies R&D UK Ltd.) is a Senior Research Scientist at the Knowledge Graph Lab. During his Ph.D., he specialized in Natural Language Generation and Knowledge Graph Embeddings research areas. Additionally, he has a keen interest in statistical learning, geometric deep learning, natural language processing, and computer vision. In the past, Sebastien has co-organized the 18th Workshop on Spoken Dialogue Systems for PhDs, PostDocs & New Researchers (YRRSDS) in Edinburgh, Scotland (2022), but also the PromptEng workshop series at TheWebConf (ex-WWW). Currently, he is one of the Program Chairs of the EMNLP 2025 Industry Track.
• Hajira Jabeen [UniKlinik] leads the ‘AI in Research Data Management’ team within the Institute for Biomedical Informatics. Her team focuses on leveraging artificial intelligence and LLMs to improve research data management practices, particularly in the biomedical field. The team works on developing scalable AI-driven tools and workflows that enhance data organization, integration, and analysis, developing innovative data-driven solutions. She has a background in both research and teaching, with previous affiliations at the University of Bonn, the University of Cologne, and ITU Copenhagen, and has organized multiple workshops and conferences in data science and informatics.
• Andre Melo (Huawei Technologies R&D UK Ltd.) is a Research Scientist leading the Knowledge-Aware Agents team at Huawei's Knowledge Graph Lab in Edinburgh. During his PhD he researched automatic error detection and completion methods for Knowledge Graphs. He also has worked with Knowledge Graph applications in the medical and Geographical Information Systems and E-commerce domains in the industry. His research interests include graph-based retrieval-augment generation methods for question answering, memory extraction and retrieval for multi-agent systems.
• Khalil Mrini (Oracle, New York City, U.S.) is an NLP researcher working as Principal Applied Scientist at OCI’s Agent Science team. He won the Dissertation Award of the Computer Science and Engineering department at the University of California San Diego for his 2022 Ph.D. thesis on Medical Question Answering. He has previously worked as Research Scientist at Meta, Bytedance (TikTok), and Grammarly, and was a research intern at Google Brain (now Deepmind), Facebook AI, Amazon Alexa, and Adobe Research. Dr. Mrini has published at ACL, EMNLP, NAACL, and at the AfricaNLP workshop at ICLR. He participates in the organization of the Arabic NLP Conference co-located with EMNLP, and is part of the organizing committee of EACL 2026 due to be held in Rabat, Morocco. He has co-founded and led affinity workshops for North Africans in NLP at various NLP conferences.

Program Committee

To be announced

Important Dates

• Abstract (OpenReview): January 15^th, 2026
• Submission: January 22^nd, 2026
• Notification: February 28^th, 2026
• Camera-ready: February 19^th, 2026
• Presentation: April XX^th, 2026