EMNLP Findings2025
Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue
Sangyeop Kim, Yohan Lee, Sanghwa Kim, Hyunjong Kim, Sungzoon Cho
摘要
Effective long-term memory in conversational AI requires synthesizing information across multiple sessions. However, current systems place excessive reasoning burden on response generation, making performance significantly dependent on model sizes. We introduce PRE-Mem (Pre-storage Reasoning for Episodic Memory), a novel approach that shifts complex reasoning processes from inference to memory construction. PREMem extracts finegrained memory fragments categorized into factual, experiential, and subjective information; it then establishes explicit relationships between memory items across sessions, capturing evolution patterns like extensions, transformations, and implications. By performing this reasoning during pre-storage rather than when generating a response, PREMem creates enriched representations while reducing computational demands during interactions. Experiments show significant performance improvements across all model sizes, with smaller models achieving results comparable to much larger baselines while maintaining effectiveness even with constrained token budgets. Code and dataset are available at https://github. com/sangyeop-kim/PREMem.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
已有 1 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。
脉络
引用它的顶会 Paper1
它引用的 Paper13
- A-Mem: Agentic Memory for LLM AgentsWujiang Xu, Zujie Liang, Kai Mei, Hang Gao 等NeurIPS 2025 · 1,138 次引用
- HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language ModelsBernal Jimenez Gutierrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga 等NeurIPS 2024 · 395 次引用
- LightRAG: Simple and Fast Retrieval-Augmented GenerationZirui Guo, Lianghao Xia, Yanhua Yu, Tu Ao 等EMNLP Findings 2025 · 209 次引用
- A Human-Inspired Reading Agent with Gist Memory of Very Long ContextsKuang-Huei Lee, Xinyun Chen, Hiroki Furuta, John F. Canny 等ICML 2024 · 106 次引用
- Curriculum Contrastive Context Denoising for Few-shot Conversational Dense RetrievalKelong Mao, Zhicheng Dou, Hongjin QianSIGIR 2022 · 40 次引用
相关 Paper
- MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic OptimizationHaidong Xin, Xinze Li, Zhenghao Liu, Yukun Yan 等ACL Findings 2026
- REMem: Reasoning with Episodic Memory in Language AgentYiheng Shu, Padmaja Jonnalagedda, Xiang Gao, Bernal Jimenez Gutierrez 等ICLR 2026 · 20 次引用
- RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM AgentsZijie Dai, Shiyuan Deng, Sheng Guan, Yizhou Tian 等ACL Findings 2026
- RGMem: Renormalization Group–inspired Memory Evolution for Language AgentsAo Tian, Yunfeng Lu, Xinxin Fan, Changhao Wang 等ICML 2026 · 2 次引用
- APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AIPratyay Banerjee, Masud Moshtaghi, Shivashankar Subramanian, Amita Misra 等ACL 2026 · 1 次引用
