Aligning Machiavellian Agents: Behavior Steering via Test-Time Policy Shaping

Add code
Nov 17, 2025
Figure 1 for Aligning Machiavellian Agents: Behavior Steering via Test-Time Policy Shaping
Figure 2 for Aligning Machiavellian Agents: Behavior Steering via Test-Time Policy Shaping
Figure 3 for Aligning Machiavellian Agents: Behavior Steering via Test-Time Policy Shaping
Figure 4 for Aligning Machiavellian Agents: Behavior Steering via Test-Time Policy Shaping

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: