# What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents

arXiv: https://arxiv.org/abs/2607.08032 · HTML: https://mlsanity.com/paper/2607.08032/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 97 of its 144 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 30 of 97)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models](https://mlsanity.com/paper/2403.06764/) (2024)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [Gated Delta Networks: Improving Mamba2 with Delta Rule](https://mlsanity.com/paper/2412.06464/) (2024)
- [Gated Linear Attention Transformers with Hardware-Efficient Training](https://mlsanity.com/paper/2312.06635/) (2023)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time](https://mlsanity.com/paper/2305.17118/) (2023)

## Built on by (most cited first, 4 of 4)

- [CrystalMem: Elastic Memory for Self-Evolving LLM Agents via Knowledge Crystallization](https://mlsanity.com/paper/2608.00303/) (2026)
- [Handover of In-Context Learning State Across Session Boundaries](https://mlsanity.com/paper/2608.14528/) (2026)
- [What Does Context Compression Cost an Agent? Interaction Costs Unrevealed by Task-Completion Metrics](https://mlsanity.com/paper/2608.16370/) (2026)
- [Dude, Where's My State? Execution Information Requirements for Stateful Agents](https://mlsanity.com/paper/2609.32687/) (2026)

## Abstract (arXiv)

Large language models, and the agents built on them, spend an ever-growing share of their compute and memory on remembering: caching attention keys and values, carrying long prompts, maintaining recurrent state, and storing what happened in previous turns and sessions. Because none of this memory is free, four largely separate research communities have each learned to compact it. They evict or quantize the KV cache, prune or distill prompts, bound architectural state, and consolidate agent memory. We argue that these are instances of one problem: a rate--distortion decision about what context-derived information to retain versus discard, at what fidelity, under a resource budget, so as to preserve downstream task utility. We make this lens precise with a single compaction objective and a layer-agnostic lower bound, use it to build a seven-axis taxonomy that classifies methods from across the stack uniformly, and use it to transfer mechanisms between layers that have never been connected, from serving-stack KV management to agent long-term memory. Two patterns hold across the survey. At every layer the signal that decides what to keep is attention magnitude or recency, and it fails in the same way everywhere, by discarding, before the query is known and with no way to undo it, information the query later needs. And while compression is measured carefully on single-turn long context, the repeated compaction that agents actually perform is almost never measured, and no benchmark holds one budget axis across all the layers at once. We turn both observations into a benchmark proposal, a small reference experiment, and a set of compaction-aware design principles, and we map the open problems.