Causal Retention in Interactive Agents: Interface Factorization and Selective Adaptation
This work studies causal retention: whether a frozen learned state answers a mechanism-probe map fixed independently of training, including action, context, direct target, value, and delay, which is distinct from task sufficiency and source-domain decodability.
Sheng-Jun Zhang, Ting Liu, Dong Xie et al.
· 0 citations