Munich🥨NLP x SAP: Knowledge Graphs & Agents
​What role do knowledge graphs play as LLMs get longer context windows and AI agents move into production?
​Join Munich🥨NLP and SAP for an evening bringing together research and industry perspectives on long-context LLMs, retrieval, knowledge graphs, and autonomous AI agents.
​Talk 1: Custom AI in Action
Riswan Lathif · SAP
​Talk 2: Needle in a Knowledge Graph
Jakob Sturm · TUM / BMW
​Two talks, food & drinks, and plenty of time to connect with Munich’s NLP and AI community.
​📅 Agenda
​17:30 | Doors open
​17:50 | Welcome & Intro
​18:00 | Talk 1: “Custom AI in Action”
Speaker: Riswan Lathif
​Abstract
​SAP's customers are varied and cover a lot of industries. Thus they also have a need to build their own custom solutions to make the best out of SAP's standard software. This presentation shows how custom AI solutions can help leverage the available AI tools to add business value and discusses ​how we move beyond promising AI prototypes and turn autonomous agents into productive, reliable workflows.
About the Speaker
Riswan is a principal software architect at Customer Industry Solutions, who specializes in building custom AI solutions. He worked in startups and the German space center DLR before joining SAP, and is an advocate of using AI responsibly to its full potential"
​18:45–18:50 | Short break
​18:50–19:35 | Talk 2: “Needle in a Knowledge Graph”
Speaker: Jakob Sturm (TUM / BMW)
​Abstract
​Do we still need retrieval when LLMs can digest increasingly large corpora through ever-growing context windows?
​This project investigates whether LLMs can reliably identify relevant information within large inputs by introducing a challenging benchmark based on knowledge graphs. It examines how model performance changes with increasing input size and how the ordering of information within the context affects an LLM’s ability to find the relevant information.
​About the Speaker
​Jakob Sturm is a PhD researcher at TUM’s Social Computing Group and BMW’s Innovation & Emerging Technologies department, supervised by Georg Groh.
​His research focuses on Information Retrieval and Retrieval-Augmented Generation (RAG), particularly on understanding when RAG is the right approach and when other methods may be more suitable. He also works on improving information retrieval for AI applications in specialized domains.
​At BMW, his industry focus is on domain-adapted RAG for quality management processes.
​19:35–21:00 | Food, drinks & networking 🍕
​🎟️ Registration
​Registration is free but subject to host approval due to limited capacity at the SAP office. If your plans change, please cancel your registration so we can offer the spot to someone else.