Rahul Marchand

I'm in my final year of engineering at Oxford. At the moment I'm at the Oxford Witt Lab with Christian Schroeder de Witt, and co-mentoring a SPAR project. My current research is on goal misgeneralisation in planning agents.

Before that I built a benchmark of container sandbox escapes for LLM agents with the UK AI Security Institute, and worked on machine learning for tuning quantum dot devices in Natalia Ares's group.

Outside work I coxed the Oxford lightweights in the 2024 and 2025 Boat Races. I'm Belgian and Sri Lankan, and grew up in London.

Publications

1. QArray+: A Physics-Informed GPU-Accelerated Simulator for Quantum Dot ArraysP. Vaidhyanathan, B. van Straaten, A. Petrillo, R. Marchand, E. De Nicolo, M. Veldhorst, B. Khailany, T. L. Patti, N. AresarXiv, 2026
2. Action-Factored Multi-Agent Reinforcement Learning for Scalable Quantum Device TuningE. De Nicolo*, R. Marchand*, C. Carlsson, P. Vaidhyanathan, N. AresarXiv, 2026
3. Quantifying Frontier LLM Capabilities for Container Sandbox EscapeR. Marchand, A. O Cathain, J. Wynne, P. M. Giavridis, S. Jennings, F. Tuxworth, T. H. Dur, S. Deverett, J. Wilkinson, J. Gwartz, H. CoppockICML 2026, oral · code
4. End-to-End Analysis of Charge Stability Diagrams with TransformersR. Marchand*, L. Schorling*, C. Carlsson, J. Schuff, B. van Straaten, T. L. Patti, F. Fedele, J. Ziegler, P. Girdhar, P. Vaidhyanathan, N. AresarXiv, 2025

* equal contribution

Writing

1. A Steerable Decision Threshold in a Planning AgentAugust 2026