1 citations · 1 across the 7 of their papers we have counts for
13 papers
Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Non-Verifiable Domains
Sumeet Ramesh Motwani, Tejas Krishnan, Alistair Letcher +10
Reinforcement learning with verifiable rewards (RLVR) has led to significant gains in math and code generation. Extending these gains to open-ended domains remains challenging: gro…
Inter-Agent Influence: Evaluating Persuasion, Deception, and Coercion in Multi-Agent Systems
Chandler Smith, Qi Guo, Cecilia Elena Tilli +6
The deployment of AI agents in multi-agent settings enables inter-agent influence, whereby agents can strategically steer each other's behaviour towards an intended outcome. Such c…
Inside the Loop: A Mechanistic Study of Weight-Tied Transformers on Depth-Bound Algorithmic Tasks
Magnus Sesodia, Juil Sock, Philip Torr +1
Solving algorithmic tasks with many sequential steps typically requires scaling up transformer depth or chain-of-thought length, incurring unfavorable parameter and inference-compu…
Can CaMeLs Talk? Securing Multi-Agent Systems Against Indirect Prompt Injection Attacks
James Peters-Gill, Avi Semler, Henning Bartsch +2
Indirect prompt injection attacks - malicious instructions embedded in content processed by large language models - remain a major obstacle to safely deploying tool-using agents. C…
ORBIT: A Framework for Multi-Agent Safety and Security Evaluations
Ben Hagag, William L. Anderson, Srija Chakraborty +1
Multi-agent LLM systems are increasingly deployed for complex, long-horizon tasks or emerge as a natural consequence of agents interacting in the wild. Yet they give rise to signif…
Entangled Representations Amplify Collateral Damage in Unlearning
Evžen Wybitul, Tim G. J. Rudner, Christian Schroeder de Witt
A long-held intuition in interpretability research is that representational entanglement, the sharing of structure between knowledge domains in a neural network, makes unlearning h…
Spatial Generalization Tests for Machine Learning-based Weather Models to Assess Physical Consistency
Maren Höver, Milan Klöwer, Christian Schroeder de Witt +1
Machine learning-based weather prediction is revolutionizing weather forecasting by learning from weather data in present-day climate. However, generalization to other climates rem…
A Note on the Strategic Confinement Problem
Christian Schroeder de Witt
Lampson's confinement problem asks how to prevent a program that processes confidential information from leaking it to a third party. We introduce the strategic confinement problem…
Detecting Multi-Agent Collusion Through Multi-Agent Interpretability
Aaron Rose, Carissa Cullen, Sahar Abdelnabi +3
Non-verbalised or secret collusion may impose a ceiling on transcript-level monitoring in multi-agent deployments. Internal model activations are known to provide an additional mon…
Chronos: The AI Co-Historian
Lorenz Hufe, Niclas Griesshaber, Gavin Greif +5
AI is increasingly supporting, accelerating, and automating scientific discovery across subjects. Yet, the adoption of AI in historical research remains limited due to the lack of…
OpenSanctions Pairs: Large-Scale Entity Matching with LLMs
Chandler Smith, Magnus Sesodia, Friedrich Lindenberg +1
We release OpenSanctions Pairs, the first large-scale public benchmark for entity matching on sanctions and OSINT data. The dataset includes 755,540 expert-labeled pairs over 1 mil…
VET Your Agent: Towards Host-Independent Autonomy via Verifiable Execution Traces
Artem Grigor, Christian Schroeder de Witt, Simon Birnbach +1
Recent advances in large language models (LLMs) have enabled a new generation of autonomous agents that operate over sustained periods and manage sensitive resources on behalf of u…
Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap
Georgia Channing, Juil Sock, Ronald Clark +2
The rapid proliferation of AI-manipulated or generated audio deepfakes poses serious challenges to media integrity and election security. Current AI-driven detection solutions lack…