An agent-centric view of data-efficient learning is developed, an agentic learning loop is formulated, data efficiency is defined as capability improvement without proportional increases in supervision or real-environment trial-and-error, and methods are synthesized into experience augmentation, agent structural design...
Yaqing Wang, Zhen-Lin Luo, Pei-Yao Zhao et al.· Proceedings of the Thirty-Fi...· 1 citation
This work shows that retrieval-head attention provides a mechanistic signal for revealing segment-level memory utilization and proposes Attention-Guided Memory Refinement (AGMR), a framework that uses utilization patterns revealed by attention to guide targeted segment-level memory updates.
Yechao Hong, Hai-Quan Qiu, Yaqing Wang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.