# Learning What Not to Forget: Long-Horizon Agent Memory from a Few Kilobytes of Learning

arXiv: https://arxiv.org/abs/2606.20954 · HTML: https://mlsanity.com/paper/2606.20954/

## 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 22 of its 32 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (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)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [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)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [ACON: Optimizing Context Compression for Long-horizon LLM Agents](https://mlsanity.com/paper/2510.00615/) (2025)
- [KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows](https://mlsanity.com/paper/2507.07400/) (2025)
- [A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2511.17208/) (2025)
- [Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs](https://mlsanity.com/paper/2512.03324/) (2025)
- [Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability](https://mlsanity.com/paper/2410.11786/) (2024)
- [Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management](https://mlsanity.com/paper/2605.06472/) (2026)

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

- [Memory Control Signals Emerge Before Action in Long Horizon Agents](https://mlsanity.com/paper/2609.27286/) (2026)
- [StateComp: Learning When to Compress History in Long Horizon Agents](https://mlsanity.com/paper/2609.27298/) (2026)
- [DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents](https://mlsanity.com/paper/2609.27276/) (2026)
- [Stable Geometry with Divergent Task Evidence for Efficient Long-Horizon Agent Compression](https://mlsanity.com/paper/2609.27332/) (2026)

## Abstract (arXiv)

Long-running language-model systems accumulate interaction history that outgrows the context window, so they must continually evict. When an eviction policy drops a task-critical detail, for example an access token issued at login or a path the next call needs, the action fails. We present LRE (Learned Relevance Eviction), a kilobyte-scale, CPU-only, language-model-free scorer that learns which units of history are task-critical and keeps them by verbatim extraction. Under a matched-budget comparison, in our experiment, no baseline dominates LRE on the accuracy-cost plane. On agents, LRE recovers 93% of the aggregate accuracy of keeping the entire history (41.1 vs. 44.0) and exceeds it by 27% on the simplest tasks, while requiring zero compressor calls and cutting the worst-case peak prompt by 52%. A controlled study trace shows LRE completes tasks where the others loop, finishing one such task in 37% fewer calls than keeping everything and solving 14 tasks where no other run policy does. On conversational memory, LRE outranks dense and token-pruning encoders at zero neural cost while being 295-1569x smaller in size. In downstream evaluation, LRE gives the best budgeted answer quality on LoCoMo reading 68% fewer tokens. Its supervision can also be annotation-free: training only on the system's own behavior recovers 95% of the supervised scorer's effectiveness. We argue that, because memory eviction in LLM agents is a fidelity problem, it requires a deployable proactive policy where the future query is unavailable and exact state is decisive, and that cheap learned relevance can be sufficient.