[1]
Mujtaba, D. et al. 2026. Aligning Machiavellian Agents: Behavior Steering via Test-Time Policy Shaping. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 44 (Mar. 2026), 37738–37746. DOI:https://doi.org/10.1609/aaai.v40i44.41109.