Laurent Bindschaedler | Systems Researcher

Research Group Leader at MPI-SWS

Laurent
Bindschaedler

I lead the Data Systems Group (DSG) at the Max Planck Institute for Software Systems.

I build next-generation systems for massive-scale data management and AI at the intersection of operating systems, databases, and machine learning.

My current focus is on analytics (graphs, blockchain, multi-modal) and AI systems beyond single models. We aim to overcome the limitations of existing systems to enable robust, adaptive, and efficient processing for complex workloads.

Prev: Postdoctoral Fellow at MIT CSAIL · Ph.D. at EPFL

Prospective Students

CV Research Statement

Research Interests

Big Data

Machine Learning

Distributed Systems

Software Architecture

Cloud Computing

Security and Privacy

Latest Blog Posts

OpinionJul 4, 2026

The Conservation of Complexity: The Ends Still Need a Middle

Everyone is predicting that AI will flatten the software stack into one English-speaking agent, until nothing of the old software remains. It will not go that far. Complexity is conserved, the end-to-end principle still collects its debt, and the stack does not flatten all the way down. It sorts itself by what you can afford to trust.

NewsJun 12, 2026

The Invisible Lottery: Algorithm Steering in LLM Code Generation at ICML 2026

New paper with Akanksha Narula and Mofasshara Rafique at ICML 2026 in Seoul. Incidental prompt cues silently decide which algorithm an LLM ships, even when every output passes the same tests.

NewsApr 20, 2026

What Survives When Code Doesn't? Keynote at EuroMLSys 2026

I am giving the keynote at EuroMLSys 2026 in Edinburgh. A short teaser on what happens to software when code becomes disposable.

NewsApr 12, 2026

ClawVM: Virtual Memory for Stateful LLM Agents at EuroMLSys 2026

New paper with Mofasshara Rafique at EuroMLSys 2026 in Edinburgh. Classical virtual memory meets agent state management.

NewsMar 16, 2026

Rebooting Microreboot: Safe Recovery for Microservices at ARCS 2026

New paper at ARCS 2026 in Mainz. We decouple agent planning from infrastructure actuation so that LLM-based remediation agents cannot cause more damage than the incident they are trying to fix.

NewsMar 12, 2026

HARNESS: A Tutorial on Hardening Always-On Agents at SOSP 2026

Akhil Arora and I are running a half-day tutorial at SOSP 2026 on building and hardening runtimes for long-lived, tool-using agents.

View All Posts

Latest Publications

Agent Flight Recorder: Tamper-Evident Audit Trails with On-Chain Anchoring for Long-Horizon Tool-Using Agents

2026

Laurent Bindschaedler, Quentin Botha, Christoph Siebenbrunner

BCCA 2026

PDF

Bonded Recourse for Smart-Contract Settlement of Compensable Agent Side Effects

2026

Laurent Bindschaedler, Quentin Botha, Christoph Siebenbrunner

BCCA 2026

PDF

The Invisible Lottery: How Subtle Cues Steer Algorithm Choice in LLM Code Generation

2026

Akanksha Narula, Mofasshara Rafique, Laurent Bindschaedler

ICML 2026

PDF

Informed Search for Regular Path Query Reachability

2026

Diego Rivera Correa, Laurent Bindschaedler

GRADES-NDA 2026

PDF

ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents

2026

Mofasshara Rafique, Laurent Bindschaedler

EuroMLSys 2026

PDF Code

View All Publications

Research Projects

Complex AI Systems

Agentic AI Infrastructure

Developing environments where multiple models and non-model components are integrated to work together efficiently. Research targets optimizing agentic workloads through advanced scheduling, caching, and resource management.

Complex AI Systems

Cache Saver

A modular, plug-and-play framework for high-level LLM inference optimizations. Cache Saver uses a namespace-aware list-valued cache to ensure statistical integrity and reproducibility, reducing inference costs by ~25% and CO2 emissions by ~35% on average.

Complex AI Systems

Code Intelligence

Research on leveraging LLMs for code-related tasks. SQL-of-Thought introduces a multi-agent framework for text-to-SQL with guided error correction, achieving state-of-the-art results on Spider. LoRACode uses parameter-efficient fine-tuning for code embeddings, reducing trainable parameters to under 2%.

Complex AI Systems

LLM-Enhanced Databases

IOLM-DB makes LLM-enhanced database queries practical through query-specific model optimization. Rather than using expensive general-purpose LLMs for all queries, we create specialized lightweight models tailored to specific analytical tasks, enabling scalable processing of millions of rows.

Learned Systems

Benchmarking Learned Systems

Traditional benchmarks fail to characterize learned systems that overfit to static workloads. We propose new benchmarks that measure adaptability through descriptive statistics and outliers, rather than average metrics, to fairly evaluate the cost and benefits of learned database components.

Learned Systems

Updateable Learned Indexes

Learned indexes promise significant performance gains over traditional B-trees, but struggle with updates. We are developing concurrently updateable learned index structures that maintain the performance benefits of learned models while supporting efficient insertions and deletions.

View All Projects

Teaching

Spring 2026