Dena Mujtaba, Brian Hu 0001, Anthony Hoogs, Arslan Basharat. Aligning Machiavellian Agents: Behavior Steering via Test-Time Policy Shaping. In Sven Koenig, Chad Jenkins, Matthew E. Taylor, editors, Fortieth AAAI Conference on Artificial Intelligence, Thirty-Eighth Conference on Innovative Applications of Artificial Intelligence, Sixteenth Symposium on Educational Advances in Artificial Intelligence, AAAI 2026, Singapore, January 20-27, 2026. pages 37738-37746, AAAI Press, 2026. [doi]
Abstract is missing.