Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction
This work shows that an agent's reliance on memory can be modeled as an explicit and user-controllable dimension, and proposes a framework that allows users to dynamically regulate memory reliance, ranging from a fresh-start mode that promotes innovation to a high-fidelity mode that closely follows interaction history.
Mu-Zhao Tian, Zi-Su Huang, Xiaohua Wang et al.
· Annual Meeting of the Associ... · 0 citations