Xun Liang

SPAR introduces a novel framework that rectifies action policies by performing local fine-tuning in a residual space anchored to a pure behavior cloning policy, achieving state-of-the-art performance in offline policy improvement.

The paper introduces RoleCDE, a novel benchmark that evaluates role-playing agents' ability to resolve conflicts between role-specific values and general alignment constraints, revealing a 'Role Value Decoupling' phenomenon.