← all datasets

MINTEval

Emerging
1papers using it
2026first seen

MINTEval is a benchmark that evaluates memory-augmented agents in long-horizon settings with highly interconnected contexts and diverse question types, focusing on their ability to handle interference and perform accurate recall and reasoning across multiple domains.

Papers using MINTEval (1)

MINTEval dataset β€” papers, benchmarks & downloads Β· Large Language Models