MemEmo: Evaluating Emotion in Memory Systems of Agents

2026-02-27

AI Summary

This study addresses the lack of systematic evaluation of emotional information processing in existing agent memory systems. To this end, it proposes the first comprehensive evaluation framework specifically designed for emotional memory, introduces the HLME dataset, and defines three core tasks: emotional information extraction, memory updating, and emotion-based question answering. The framework is used to empirically assess a range of mainstream and state-of-the-art memory architectures. Experimental results reveal significant performance deficiencies across all three tasks, highlighting critical limitations in how current systems model emotional memory. These findings not only underscore the need for more nuanced affective reasoning in memory mechanisms but also provide clear directions for future research and system improvement.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Humans and AI: Emotional Intelligence
• Natural Language Processing: Information Extraction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

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.

Problem

• emotion
• memory systems
• evaluation benchmark
• affective information
• emotional memory

Innovation

• emotion-enhanced memory
• memory evaluation benchmark
• HLME dataset
• affective information processing
• emotional memory updating