# Compact-Memory LLM Agents via Online Max-Member Clustering and Atom-Aware Packing

arXiv: https://arxiv.org/abs/2609.04915 · HTML: https://mlsanity.com/paper/2609.04915/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 22 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Placed in

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

## Builds on (most cited first, 17 of 17)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [ACON: Optimizing Context Compression for Long-horizon LLM Agents](https://mlsanity.com/paper/2510.00615/) (2025)
- [From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs](https://mlsanity.com/paper/2504.15965/) (2025)
- [HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model](https://mlsanity.com/paper/2408.09559/) (2024)
- [Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers](https://mlsanity.com/paper/2603.07670/) (2026)
- [AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications](https://mlsanity.com/paper/2602.22769/) (2026)
- [Active Context Compression: Autonomous Memory Management in LLM Agents](https://mlsanity.com/paper/2601.07190/) (2026)
- [Latent Context Compilation: Distilling Long Context into Compact Portable Memory](https://mlsanity.com/paper/2602.21221/) (2026)
- [Memori: A Persistent Memory Layer for Efficient, Context-Aware LLM Agents](https://mlsanity.com/paper/2603.19935/) (2026)

## Abstract (arXiv)

Many long-horizon LLM deployments face tight prompt budgets: latency, cost, and context limits make full-context prompting impractical as interaction length grows. The key question is then not raw recall alone, but which memory design gives the best quality--token trade-off in the compact-memory regime. We present RSM-full, an online clustered-memory pipeline designed for a strong quality--token Pareto point. RSM-full combines two design choices: a cosine-gated max-member merge write rule and an atom-aware grouped context packer. On AMA-Bench, our primary compact-memory benchmark, it reaches 83% of Full-Context quality at 32% of the token cost at a 4k budget; under four-seed averaging it beats the closest streaming-clustered baseline (Online K-Means) by +3.5--6.0,pp (p<.001) across the whole ~2.6k--~5k regime. Three-seed ablations show most of this gain comes from the merge rule (+5.7,pp over Online K-Means and matched-τ DP-means) and the grouped packer (+5.0,pp over flat concatenation). The pattern reproduces on RealMem, an independent long-horizon persona-memory benchmark: RSM-full improves on Budget-RAG (+0.69,pp, p=.006), is on par with BM25-RAG (paired Delta=+0.27,pp, p=.47; we do not claim BM25 equivalence in the equivalence-test sense), and significantly outperforms Streaming-Proto (+2.97,pp) and the closest reproduced 2025 agentic-memory baseline A-MEM (+1.65,pp, p<.001). Across benchmarks the message is consistent: under tight budgets, compact-memory performance is driven mainly by how streaming memories are merged and how retrieved content is assembled. Overall, RSM-full is most useful when answeroughly 2k--5k prompt tokens, where itdefines a strong compact-memory Pareto point; higher-token baselines remain stronger outside this regime.