
Data Systems Group
Max Planck Institute for Software Systems
Runtime guarantees for AI agents, and data systems for AI
About the Group
The Data Systems Group (DSG) at MPI-SWS builds systems for AI agents and data-intensive AI applications. We build prototypes, measure them on real workloads, and release code where we can.
Our current work covers runtime guarantees for AI agents, language models inside database systems, reproducible LLM pipelines, and large-scale graph learning. We collaborate with academic groups and industry partners in Europe and North America.
Learn more about our team
Laurent Bindschaedler
Research Group Leader
Runtime guarantees for AI agents, data systems for AI, and distributed systems.
Personal websiteResearch Areas
We work in four areas: agent runtimes, data systems for AI, trustworthy AI, and graph systems.
Agentic AI Infrastructure
Runtime contracts for AI agents: when an action becomes permanent, what state an agent keeps, and tamper-evident records of what it did.
Data Systems for AI
Language models as database operators, semantic caching for OLAP, and reproducible, lower-cost LLM pipelines.
Trustworthy AI
Measuring how context steers what models generate, and who decides what counts as correct when agents repair code.
Graph Systems
Gradient-only communication for large-scale GNN training, graph partitioning, and graph query evaluation.
Recent Publications
Our latest research
ClawMMU: Protection-Coherent Virtual Memory for Stateful LLM Agents
2026AgenticOS Workshop at NeurIPS 2026
Jinhao Hu, Bardia Mohammadi, Mofasshara Binte Rafique, Lars Henning Klein, Akhil Arora, Ashvin Goel, Laurent Bindschaedler
Agent Flight Recorder: Tamper-Evident Audit Trails with On-Chain Anchoring for Long-Horizon Tool-Using Agents
2026BCCA 2026
Laurent Bindschaedler, Quentin Botha, Christoph Siebenbrunner
Bonded Recourse for Smart-Contract Settlement of Compensable Agent Side Effects
2026BCCA 2026
Laurent Bindschaedler, Quentin Botha, Christoph Siebenbrunner
Ghost Tool Calls: Issue-Time Privacy for Speculative Agent Tools
2026REALM 2026
Bardia Mohammadi, Lars Henning Klein, Akhil Arora, Laurent Bindschaedler
Latest News
Updates from the Data Systems Group
Talk at the EPFL AI Center
Laurent will give a talk in the EPFL AI Center's AI Fundamentals seminar series on November 24, 2026: "A Systems Approach to Safe and Reliable Agents: Four Contracts for Agent Runtimes," on the effect, state, composition, and intent contracts that an agent runtime should state.
November 2026
EventTalk at the Knowledge Bases and Agents for CERN Workshop
Laurent gave a talk at the Knowledge Bases and Agents for CERN workshop in Geneva: "Agents Propose, Mediators Act: Safe Actions for Operations Agents," on letting operations agents propose typed actions that a small trusted mediator checks and runs. The slides are online.
October 2026
PublicationFour Non-Archival Workshop Papers on Agent Runtimes
Ghost Tool Calls, When to Cross the Rubicon, and The Working Set of a Coding Agent at REALM 2026, and ClawMMU at the AgenticOS Workshop at NeurIPS 2026.
October 2026
Join Our Group
We are hiring PhD students, postdocs, and interns with a systems background. If you are interested in joining us, get in touch.
Get in Touch