# Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations

arXiv: https://arxiv.org/abs/2402.11975 · HTML: https://mlsanity.com/paper/2402.11975/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://mlsanity.com/paper/1603.08023/) (2016)
- [Beyond Goldfish Memory: Long-Term Open-Domain Conversation](https://mlsanity.com/paper/2107.07567/) (2021)
- [Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT](https://mlsanity.com/paper/2302.10198/) (2023)
- [Towards Making the Most of ChatGPT for Machine Translation](https://mlsanity.com/paper/2303.13780/) (2023)
- [Long Time No See! Open-Domain Conversation with Long-Term Persona Memory](https://mlsanity.com/paper/2203.05797/) (2022)
- [Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models](https://mlsanity.com/paper/2303.13809/) (2023)
- [ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark](https://mlsanity.com/paper/2303.13648/) (2023)
- [Memformer: A Memory-Augmented Transformer for Sequence Modeling](https://mlsanity.com/paper/2010.06891/) (2020)
- [Keep Me Updated! Memory Management in Long-term Conversations](https://mlsanity.com/paper/2210.08750/) (2022)
- [Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations](https://mlsanity.com/paper/2310.20246/) (2023)
- [Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering](https://mlsanity.com/paper/2109.03381/) (2021)
- [End-to-end Spoken Conversational Question Answering: Task, Dataset and Model](https://mlsanity.com/paper/2204.14272/) (2022)
- [Adaptive Bi-directional Attention: Exploring Multi-Granularity Representations for Machine Reading Comprehension](https://mlsanity.com/paper/2012.10877/) (2020)
- [History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System](https://mlsanity.com/paper/2302.00907/) (2023)
- [From Good to Great: Improving Math Reasoning with Tool-Augmented Interleaf Prompting](https://mlsanity.com/paper/2401.05384/) (2023)
- [Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation](https://mlsanity.com/paper/2103.01534/) (2021)
- [Xu at SemEval-2022 Task 4: Pre-BERT Neural Network Methods vs Post-BERT RoBERTa Approach for Patronizing and Condescending Language Detection](https://mlsanity.com/paper/2211.06874/) (2022)
- [Effortless Integration of Memory Management into Open-Domain Conversation Systems](https://mlsanity.com/paper/2305.13973/) (2023)
- [Improve Retrieval-based Dialogue System via Syntax-Informed Attention](https://mlsanity.com/paper/2303.06605/) (2023)

## Built on by (most cited first, 30 of 36)

- [HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model](https://mlsanity.com/paper/2408.09559/) (2024)
- [Towards Lifelong Dialogue Agents via Timeline-based Memory Management](https://mlsanity.com/paper/2406.10996/) (2024)
- [LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions](https://mlsanity.com/paper/2509.18970/) (2025)
- [The Oscars of AI Theater: A Survey on Role-Playing with Language Models](https://mlsanity.com/paper/2407.11484/) (2024)
- [Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics](https://mlsanity.com/paper/2505.00675/) (2025)
- [Cognitive Memory in Large Language Models](https://mlsanity.com/paper/2504.02441/) (2025)
- [From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents](https://mlsanity.com/paper/2505.19549/) (2025)
- [Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs](https://mlsanity.com/paper/2502.20968/) (2025)
- [Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory](https://mlsanity.com/paper/2508.08997/) (2025)
- [Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue](https://mlsanity.com/paper/2509.10852/) (2025)
- [All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolution](https://mlsanity.com/paper/2603.19595/) (2026)
- [MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialogues](https://mlsanity.com/paper/2509.11860/) (2025)
- [SHARE: Shared Memory-Aware Open-Domain Long-Term Dialogue Dataset Constructed from Movie Script](https://mlsanity.com/paper/2410.20682/) (2024)
- [MemRefine: LLM-Guided Compression for Long-Term Agent Memory](https://mlsanity.com/paper/2606.13177/) (2026)
- [Codifying Character Logic in Role-Playing](https://mlsanity.com/paper/2505.07705/) (2025)
- [Role-Playing Evaluation for Large Language Models](https://mlsanity.com/paper/2505.13157/) (2025)
- [From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents](https://mlsanity.com/paper/2607.16621/) (2026)
- [MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents](https://mlsanity.com/paper/2605.00356/) (2026)
- [MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation](https://mlsanity.com/paper/2604.08782/) (2026)
- [Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory](https://mlsanity.com/paper/2605.00702/) (2026)
- [PGMem: Tightly Coupled Persona-Memory Graph for Lifelong Personalized Agents](https://mlsanity.com/paper/2608.01708/) (2026)
- [When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agents](https://mlsanity.com/paper/2609.03467/) (2026)
- [DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Agent Memory](https://mlsanity.com/paper/2605.22411/) (2026)
- [G-Long: Graph-Enhanced Memory Management for Efficient Long-Term Dialogue Agents](https://mlsanity.com/paper/2606.13115/) (2026)
- [Ontology Memory-Augmented ASR Correction for Long Text-Speech Interleaved Conversations](https://mlsanity.com/paper/2606.13464/) (2026)
- [Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges](https://mlsanity.com/paper/2608.17605/) (2026)
- [Disentangling Long-Term Memory via Latent Neuro-Symbolic Reasoning](https://mlsanity.com/paper/2609.18461/) (2026)
- [Scene-Aware Memory Discrimination: Deciding Which Personal Knowledge Stays](https://mlsanity.com/paper/2602.11607/) (2026)
- [SOMA: Efficient Multi-turn LLM Serving via Small Language Model](https://mlsanity.com/paper/2605.11317/) (2026)
- [Improving Multi-turn Dialogue Consistency with Self-Recall Thinking](https://mlsanity.com/paper/2605.15102/) (2026)

## Abstract (arXiv)

Existing retrieval-based methods have made significant strides in maintaining long-term conversations. However, these approaches face challenges in memory database management and accurate memory retrieval, hindering their efficacy in dynamic, real-world interactions. This study introduces a novel framework, COmpressive Memory-Enhanced Dialogue sYstems (COMEDY), which eschews traditional retrieval modules and memory databases. Instead, COMEDY adopts a "One-for-All" approach, utilizing a single language model to manage memory generation, compression, and response generation. Central to this framework is the concept of compressive memory, which intergrates session-specific summaries, user-bot dynamics, and past events into a concise memory format. To support COMEDY, we curated a large-scale Chinese instruction-tuning dataset, Dolphin, derived from real user-chatbot interactions. Comparative evaluations demonstrate COMEDY's superiority over traditional retrieval-based methods in producing more nuanced and human-like conversational experiences. Our codes are available at https://github.com/nuochenpku/COMEDY.