# CarMem: Enhancing Long-Term Memory in LLM Voice Assistants through Category-Bounding

arXiv: https://arxiv.org/abs/2501.09645 · HTML: https://mlsanity.com/paper/2501.09645/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 16 Jan 2025.

## Builds on (most cited first, 12 of 12)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Beyond Goldfish Memory: Long-Term Open-Domain Conversation](https://mlsanity.com/paper/2107.07567/) (2021)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [The Second Conversational Intelligence Challenge (ConvAI2)](https://mlsanity.com/paper/1902.00098/) (2019)
- [Long Time No See! Open-Domain Conversation with Long-Term Persona Memory](https://mlsanity.com/paper/2203.05797/) (2022)
- [SCM: Enhancing Large Language Model with Self-Controlled Memory Framework](https://mlsanity.com/paper/2304.13343/) (2023)
- [Keep Me Updated! Memory Management in Long-term Conversations](https://mlsanity.com/paper/2210.08750/) (2022)
- [Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation](https://mlsanity.com/paper/2310.07397/) (2023)

## Built on by (most cited first, 9 of 9)

- [From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents](https://mlsanity.com/paper/2505.19549/) (2025)
- [Evaluating Memory Structure in LLM Agents](https://mlsanity.com/paper/2602.11243/) (2026)
- [CAR-bench: Evaluating the Consistency and Limit-Awareness of LLM Agents under Real-World Uncertainty](https://mlsanity.com/paper/2601.22027/) (2026)
- [CAIM: Development and Evaluation of a Cognitive AI Memory Framework for Long-Term Interaction with Intelligent Agents](https://mlsanity.com/paper/2505.13044/) (2025)
- [Tracing the Data Trail: A Survey of Data Provenance, Transparency and Traceability in LLMs](https://mlsanity.com/paper/2601.14311/) (2026)
- [Agent2Agent Threats in Safety-Critical LLM Assistants: A Human-Centric Taxonomy](https://mlsanity.com/paper/2602.05877/) (2026)
- [What Are You Doing? Effects of Intermediate Feedback from Agentic LLM In-Car Assistants During Multi-Step Processing](https://mlsanity.com/paper/2602.15569/) (2026)
- [CoreMem: Riemannian Retrieval and Fisher-Guided Distillation for Long-Term Memory in Dialogue Agents](https://mlsanity.com/paper/2606.18406/) (2026)
- [From Acoustic Sensing to Physical Actions: A Comprehensive Survey of Security Risks in Edge-Deployed Audio LLM-Based Agents](https://mlsanity.com/paper/2610.15390/) (2026)

## Abstract (arXiv)

In today's assistant landscape, personalisation enhances interactions, fosters long-term relationships, and deepens engagement. However, many systems struggle with retaining user preferences, leading to repetitive user requests and disengagement. Furthermore, the unregulated and opaque extraction of user preferences in industry applications raises significant concerns about privacy and trust, especially in regions with stringent regulations like Europe. In response to these challenges, we propose a long-term memory system for voice assistants, structured around predefined categories. This approach leverages Large Language Models to efficiently extract, store, and retrieve preferences within these categories, ensuring both personalisation and transparency. We also introduce a synthetic multi-turn, multi-session conversation dataset (CarMem), grounded in real industry data, tailored to an in-car voice assistant setting. Benchmarked on the dataset, our system achieves an F1-score of .78 to .95 in preference extraction, depending on category granularity. Our maintenance strategy reduces redundant preferences by 95% and contradictory ones by 92%, while the accuracy of optimal retrieval is at .87. Collectively, the results demonstrate the system's suitability for industrial applications.