MemEmo: Evaluating Emotion in Memory Systems of Agents

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Peng, Tao, Zhen, Zhao, Jihao, Chen, Ding, Zhang, Yansong, Li, Cuiping, Li, Zhiyu, Chen, Hong
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918359960911872
author Liu, Peng
Tao, Zhen
Zhao, Jihao
Chen, Ding
Zhang, Yansong
Li, Cuiping
Li, Zhiyu
Chen, Hong
author_facet Liu, Peng
Tao, Zhen
Zhao, Jihao
Chen, Ding
Zhang, Yansong
Li, Cuiping
Li, Zhiyu
Chen, Hong
contents Memory systems address the challenge of context loss in Large Language Model during prolonged interactions. However, compared to human cognition, the efficacy of these systems in processing emotion-related information remains inconclusive. To address this gap, we propose an emotion-enhanced memory evaluation benchmark to assess the performance of mainstream and state-of-the-art memory systems in handling affective information. We developed the \textbf{H}uman-\textbf{L}ike \textbf{M}emory \textbf{E}motion (\textbf{HLME}) dataset, which evaluates memory systems across three dimensions: emotional information extraction, emotional memory updating, and emotional memory question answering. Experimental results indicate that none of the evaluated systems achieve robust performance across all three tasks. Our findings provide an objective perspective on the current deficiencies of memory systems in processing emotional memories and suggest a new trajectory for future research and system optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2602_23944
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MemEmo: Evaluating Emotion in Memory Systems of Agents
Liu, Peng
Tao, Zhen
Zhao, Jihao
Chen, Ding
Zhang, Yansong
Li, Cuiping
Li, Zhiyu
Chen, Hong
Computation and Language
Memory systems address the challenge of context loss in Large Language Model during prolonged interactions. However, compared to human cognition, the efficacy of these systems in processing emotion-related information remains inconclusive. To address this gap, we propose an emotion-enhanced memory evaluation benchmark to assess the performance of mainstream and state-of-the-art memory systems in handling affective information. We developed the \textbf{H}uman-\textbf{L}ike \textbf{M}emory \textbf{E}motion (\textbf{HLME}) dataset, which evaluates memory systems across three dimensions: emotional information extraction, emotional memory updating, and emotional memory question answering. Experimental results indicate that none of the evaluated systems achieve robust performance across all three tasks. Our findings provide an objective perspective on the current deficiencies of memory systems in processing emotional memories and suggest a new trajectory for future research and system optimization.
title MemEmo: Evaluating Emotion in Memory Systems of Agents
topic Computation and Language
url https://arxiv.org/abs/2602.23944