Jonathan Kutasov

According to our database, Jonathan Kutasov authored at least 3 papers in 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Evaluating Control Protocols for Untrusted AI Agents.

Jonathan Kutasov, Chloe Loughridge, Yuqi Sun, Henry Sleight, Buck Shlegeris, Tyler Tracy, Joe Benton

CoRR, November, 2025

Optimizing AI Agent Attacks With Synthetic Data.

Chloe Loughridge, Paul Colognese, Avery Griffin, Tyler Tracy, Jonathan Kutasov, Joe Benton

CoRR, November, 2025

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents.

Jonathan Kutasov, Yuqi Sun, Paul Colognese, Teun van der Weij, Linda Petrini, Chen Bo Calvin Zhang, John Hughes, Xiang Deng, Henry Sleight, Tyler Tracy, Buck Shlegeris, Joe Benton

CoRR, June, 2025