2 papers
cs.AI2026
MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing
Nishant Bhargava, Rodrigo Sobral Barrento
Long-term LLM agents must compress streams of past interactions into persistent memory before future queries are known. Existing evaluations usually measure final question-answerin…
cs.CL2025
Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness
Lang Xiong, Nishant Bhargava, Jianhang Hong +4
Large Language Models (LLMs) often exhibit significant behavioral shifts when they perceive a change from a real-world deployment context to a controlled evaluation setting, a phen…