ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents

• URL: http://arxiv.org/abs/2605.27240v1
• Date: Tue, 26 May 2026 16:22:35 GMT
• Title: ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents
• Abstract summary: We introduce ENPMR-Bench, a benchmark for evaluating Emotional Need-aware Proactive Memory Retrieval.<n> ENPMR-Bench includes over 1,800 memory-augmented dialogues and defines structured mappings between emotional needs and supportive memory types.
• Score: 53.83618283684421
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Memory-augmented language agents are increasingly deployed in affective applications such as emotional support, where understanding and responding to users' latent emotional needs is critical. However, existing research often treats memory as a tool for factual retrieval, overlooking its role in shaping users' emotional experiences. In this work, we introduce ENPMR-Bench, a benchmark for evaluating Emotional Need-aware Proactive Memory Retrieval (ENPMR), a core capability that enables agents to infer users' latent emotional needs and proactively retrieve appropriate memories to support empathetic interaction. Grounded in Maslow's hierarchy of needs, ENPMR-Bench includes over 1,800 memory-augmented dialogues and defines structured mappings between emotional needs and supportive memory types. Experimental results demonstrate that current retrieval paradigms, including both embedding-based and LLM-driven approaches, exhibit substantial deficiencies, with empathy scores significantly lagging behind golden memory conditions. While chain-of-thought prompting improves the alignment between inferred emotional needs and retrieved memories to some extent, a notable performance gap remains. Together, these findings reveal critical limitations in current agents and outline directions for advancing personalized emotional support through need-sensitive memory retrieval.

Related papers

• A-MBER: Affective Memory Benchmark for Emotion Recognition [3.9870633524104107]
  We introduce A-MBER, an Affective Memory Benchmark for Emotion Recognition.<n>A-MBER focuses on present affective interpretation grounded in remembered multi-session interaction history.<n>Results show that A-MBER is especially discriminative on the subsets it is designed to stress.
  arXiv  Detail & Related papers  (2026-04-08T12:36:18Z)
• AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents [49.63422082885992]
  We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents.<n>AdaMem organizes dialogue history into working, episodic, persona, and graph memories.<n>We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling.
  arXiv  Detail & Related papers  (2026-03-17T13:22:54Z)
• MemEmo: Evaluating Emotion in Memory Systems of Agents [30.12443912702673]
  We propose an emotion-enhanced memory evaluation benchmark to assess the performance of memory systems in handling affective information.<n>We developed the textbfHuman-textbfLike textbfMemory textbfEmotion (textbfHLME) dataset, which evaluates memory systems across three dimensions.<n> Experimental results indicate that none of the evaluated systems achieve robust performance across all three tasks.
  arXiv  Detail & Related papers  (2026-02-27T11:46:08Z)
• Memory-guided Prototypical Co-occurrence Learning for Mixed Emotion Recognition [56.00118641432005]
  We propose a Memory-guided Prototypical Co-occurrence Learning framework that explicitly models emotion co-occurrence patterns.<n>Inspired by human cognitive memory systems, we introduce a memory retrieval strategy to extract semantic-level co-occurrence associations.<n>Our model learns affectively informative representations for accurate emotion distribution prediction.
  arXiv  Detail & Related papers  (2026-02-24T04:11:25Z)
• Rethinking Memory Mechanisms of Foundation Agents in the Second Half: A Survey [211.01908189012184]
  Memory, with hundreds of papers released this year, emerges as the critical solution to fill the utility gap.<n>We provide a unified view of foundation agent memory along three dimensions.<n>We then analyze how memory is instantiated and operated under different agent topologies.
  arXiv  Detail & Related papers  (2026-01-14T07:38:38Z)
• Evaluating Long-Term Memory for Long-Context Question Answering [100.1267054069757]
  We present a systematic evaluation of memory-augmented methods using LoCoMo, a benchmark of synthetic long-context dialogues annotated for question-answering tasks.<n>Our findings show that memory-augmented approaches reduce token usage by over 90% while maintaining competitive accuracy.
  arXiv  Detail & Related papers  (2025-10-27T18:03:50Z)
• The Emotion-Memory Link: Do Memorability Annotations Matter for Intelligent Systems? [1.960641679592198]
  We investigate the relationship between perceived group emotions (Pleasure-Arousal) and group memorability in the context of conversational interactions.<n>Our results show that the observed relationship between affect and memorability annotations cannot be reliably distinguished from what might be expected under random chance.
  arXiv  Detail & Related papers  (2025-07-18T17:06:34Z)
• In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents [70.12342024019044]
  Large Language Models (LLMs) have made significant progress in open-ended dialogue, yet their inability to retain and retrieve relevant information limits their effectiveness.<n>We propose Reflective Memory Management (RMM), a novel mechanism for long-term dialogue agents, integrating forward- and backward-looking reflections.<n>RMM shows more than 10% accuracy improvement over the baseline without memory management on the LongMemEval dataset.
  arXiv  Detail & Related papers  (2025-03-11T04:15:52Z)
• Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrieval [30.579043495085777]
  We propose an emotion-aware memory retrieval framework, termed Emotional RAG, which recalls the related memory with consideration of emotional state in role-playing agents. Our framework outperforms the method without considering the emotional factor in maintaining the personalities of role-playing agents.
  arXiv  Detail & Related papers  (2024-10-30T14:08:50Z)
• MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation [15.64077949677469]
  We present a novel Memory-Augmented Dialogue Benchmark (MADail-Bench) to evaluate the effectiveness of memory-augmented dialogue systems (MADS) The benchmark assesses two tasks separately: memory retrieval and memory recognition with the incorporation of both passive and proactive memory recall data. Results from cutting-edge embedding models and large language models on this benchmark indicate the potential for further advancement.
  arXiv  Detail & Related papers  (2024-09-23T17:38:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.