Showing cs.CLShow all
2 papers · 1 filter
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.CL2026
Calibrating Model-Based Evaluation Metrics for Summarization
Hongye Liu, Dhanajit Brahma, Ricardo Henao
Recent advances in summary evaluation are based on model-based metrics to assess quality dimensions, such as completeness, conciseness, and faithfulness. However, these methods oft…