# Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue

arXiv: https://arxiv.org/abs/2509.10852 · HTML: https://mlsanity.com/paper/2509.10852/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 53 references that are in the map.
- First posted on arXiv 13 Sep 2025.

## Builds on (most cited first, 18 of 18)

- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [From RAG to Memory: Non-Parametric Continual Learning for Large Language Models](https://mlsanity.com/paper/2502.14802/) (2025)
- [A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts](https://mlsanity.com/paper/2402.09727/) (2024)
- [User Behavior Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2306.02552/) (2023)
- [From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs](https://mlsanity.com/paper/2504.15965/) (2025)
- [Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://mlsanity.com/paper/2406.05925/) (2024)
- [On Memory Construction and Retrieval for Personalized Conversational Agents](https://mlsanity.com/paper/2502.05589/) (2025)
- [Keep Me Updated! Memory Management in Long-term Conversations](https://mlsanity.com/paper/2210.08750/) (2022)
- [Human-inspired Episodic Memory for Infinite Context LLMs](https://mlsanity.com/paper/2407.09450/) (2024)
- [Towards Lifelong Dialogue Agents via Timeline-based Memory Management](https://mlsanity.com/paper/2406.10996/) (2024)
- [Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations](https://mlsanity.com/paper/2402.11975/) (2024)
- [Are Large Language Models Temporally Grounded?](https://mlsanity.com/paper/2311.08398/) (2023)
- [Personalized Large Language Model Assistant with Evolving Conditional Memory](https://mlsanity.com/paper/2312.17257/) (2023)
- [TReMu: Towards Neuro-Symbolic Temporal Reasoning for LLM-Agents with Memory in Multi-Session Dialogues](https://mlsanity.com/paper/2502.01630/) (2025)

## Built on by (most cited first, 18 of 18)

- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2511.17208/) (2025)
- [Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations](https://mlsanity.com/paper/2602.19320/) (2026)
- [StructMem: Structured Memory for Long-Horizon Behavior in LLMs](https://mlsanity.com/paper/2604.21748/) (2026)
- [Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents](https://mlsanity.com/paper/2601.07468/) (2026)
- [Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions](https://mlsanity.com/paper/2602.22680/) (2026)
- [AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents](https://mlsanity.com/paper/2512.23343/) (2025)
- [Convomem Benchmark: Why Your First 150 Conversations Don't Need RAG](https://mlsanity.com/paper/2511.10523/) (2025)
- [Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory](https://mlsanity.com/paper/2602.15313/) (2026)
- [LeanMem: Simple and Efficient Long-Term Memory for LLM Agents](https://mlsanity.com/paper/2608.03463/) (2026)
- [Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agents](https://mlsanity.com/paper/2607.15657/) (2026)
- [Mnemon: Raw Records, Fast Judgments, Slow Thoughts](https://mlsanity.com/paper/2609.36059/) (2026)
- [MemAdapter: Fast Alignment across Agent Memory Paradigms via Generative Subgraph Retrieval](https://mlsanity.com/paper/2602.08369/) (2026)
- [TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation](https://mlsanity.com/paper/2604.07894/) (2026)
- [From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents](https://mlsanity.com/paper/2605.25693/) (2026)
- [Implicit Graph, Explicit Retrieval: Towards Efficient and Interpretable Long-horizon Memory for Large Language Models](https://mlsanity.com/paper/2601.03417/) (2026)
- [Reconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long Context](https://mlsanity.com/paper/2608.25655/) (2026)
- [Mem++: Non-Destructive Memory for Long-Term Organizational LLM Agents](https://mlsanity.com/paper/2610.02002/) (2026)

## Abstract (arXiv)

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 PREMem (Pre-storage Reasoning for Episodic Memory), a novel approach that shifts complex reasoning processes from inference to memory construction. PREMem extracts fine-grained 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.