Munich🥨NLP x SAP: Knowledge Graphs & Agents
Details
# Munich🥨NLP x SAP: Knowledge Graphs & Agents
## ⚠️ Please register on Luma
Registration for this event is handled exclusively through Luma:
https://luma.com/b6n5x3by?tk=XhPdL7
Marking yourself as attending on Meetup does not reserve a place. Your attendance is confirmed only after you have registered and received approval through Luma.
Registration is free, but capacity at the SAP office is limited. If your plans change, please cancel your Luma registration so the place can be offered to someone else.
***
Hello Munich NLP enthusiasts!
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, information retrieval, knowledge graphs, and autonomous AI agents.
The evening features two talks:
- SAP will explore the engineering challenges involved in turning autonomous-agent prototypes into reliable production workflows—and how knowledge graphs can help ground these systems.
- Jakob Sturm from TUM and BMW will examine whether increasingly long context windows can replace retrieval, using a challenging knowledge-graph benchmark.
Expect two technical talks, food and drinks, and plenty of time to meet researchers, engineers, students, and other members of Munich’s NLP and AI community.
***
## 📅 Agenda
### 17:30 | Doors open
Arrive, check in, and meet other attendees.
### 17:50 | Welcome and introduction
Welcome from SAP and Munich🥨NLP.
### 18:00–18:45 | Talk 1: “Engineering Autonomous Industry Agents in Production”
Speaker: To be announced
Organization: SAP
#### Abstract
How do we move beyond promising AI prototypes and turn autonomous agents into productive, reliable workflows?
This talk will explore the engineering challenges involved in bringing autonomous AI agents into real-world industry environments. It will look at the journey from experimentation to production and discuss the role of knowledge graphs in grounding AI systems and enabling robust real-world deployments.
### 18:45–18:50 | Short break
### 18:50–19:35 | Talk 2: “Needle in a Knowledge Graph”
Speaker: Jakob Sturm
Affiliations: 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.
The research examines how model performance changes as input size increases and how the ordering of information within the context affects an LLM’s ability to locate 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, 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 and networking 🍕
Continue the discussion with the speakers and connect with Munich’s NLP, machine-learning, and AI community.
***
## 🔍 Event details
📍 Location: SAP, Friedrich-Ludwig-Bauer-Straße 5, 85748 Garching bei München
📅 Date: Tuesday, August 25, 2026
⏰ Time: 17:30–21:00
🎤 Format: In person
🍕 Food and drinks: Available during the networking portion
***
## 🎯 Why attend?
- Learn what it takes to move autonomous AI agents from experimentation into production.
- Explore how knowledge graphs can improve grounding and reliability in agentic systems.
- Examine whether long-context LLMs reduce—or simply change—the need for retrieval.
- Hear perspectives spanning academic research and industrial deployment.
- Connect with Munich’s NLP, machine-learning, and AI community.
***
## 🎟️ Registration
Please register through Luma:
https://luma.com/b6n5x3by?tk=XhPdL7
Registration is free but subject to host approval because capacity at the SAP office is limited.
A Meetup RSVP alone is not sufficient and does not reserve a place. Please use the Luma link above to request attendance.