23 citations · 28 across the 8 of their papers we have counts for
8 papers
Architecture Matters for Multi-Agent Security
Ben Hagag, William L. Anderson, Christian Schroeder de Witt +1
Multi-agent systems (MAS), composed of networks of two or more autonomous AI agents, have become increasingly popular in production deployments, yet introduce security risks that d…
Sensitivity Analysis for Climate Science with Generative Flow Models
Alex Dobra, Jakiw Pidstrigach, Tim Reichelt +6
Sensitivity analysis is a cornerstone of climate science, essential for understanding phenomena ranging from storm intensity to long-term climate feedbacks. However, computing thes…
Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents
Christian Schroeder de Witt, Klaudia Krawiecka, Igor Krawczuk +21
AI agents are beginning to interact with each other directly and across internet platforms and physical environments, creating security challenges beyond traditional cybersecurity…
AnnoCaseLaw: Legal Annotation Benchmark of Civil Negligence
Magnus Sesodia, Rilton Franzone, Alina Petrova +7
Language models offer a way to scale costly, labour-intensive expert annotation, but their ability to reproduce expert judgements remains uncertain. This is particularly challengin…
Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems
Pierre Peigne-Lefebvre, Mikolaj Kniejski, Filip Sondej +4
As AI agents are increasingly adopted to collaborate on complex objectives, ensuring the security of autonomous multi-agent systems becomes crucial. We develop simulations of agent…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1168
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
MAD-Sherlock: Multi-Agent Debate for Visual Misinformation Detection
Kumud Lakara, Georgia Channing, Christian Rupprecht +4
One of the most challenging forms of misinformation involves pairing images with misleading text to create false narratives. Existing AI-driven detection systems often require doma…
Efficient Dictionary Learning with Switch Sparse Autoencoders
Anish Mudide, Joshua Engels, Eric J. Michaud +2
Sparse autoencoders (SAEs) are a recent technique for decomposing neural network activations into human-interpretable features. However, in order for SAEs to identify all features…