2 papers
cs.CL2026
SAGE: A Novelty Gate for Efficient Memory Evolution in Agentic LLMs
Sijia Wang, Dhanajit Brahma, Ricardo Henao
Agentic LLMs must continuously decide whether newly extracted facts should be added, merged with existing memories, or ignored, yet prior work has focused more on retrieval and sto…
cs.LG2026
Model Recycling Framework for Multi-Source Data-Free Supervised Transfer Learning
Sijia Wang, Ricardo Henao
Increasing concerns for data privacy and other difficulties associated with retrieving source data for model training have created the need for source-free transfer learning, in wh…