# Beyond Heuristics: A Decision-Theoretic Framework for Agent Memory Management

arXiv: https://arxiv.org/abs/2512.21567 · HTML: https://mlsanity.com/paper/2512.21567/

## 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 15 of its 30 references that are in the map.
- First posted on arXiv 25 Dec 2025.

## Placed in

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

## Builds on (most cited first, 15 of 15)

- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent](https://mlsanity.com/paper/2507.02259/) (2025)
- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [Neural Episodic Control](https://mlsanity.com/paper/1703.01988/) (2017)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [Large Memory Layers with Product Keys](https://mlsanity.com/paper/1907.05242/) (2019)
- [Neural Map: Structured Memory for Deep Reinforcement Learning](https://mlsanity.com/paper/1702.08360/) (2017)
- [MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems](https://mlsanity.com/paper/2510.17281/) (2025)
- [Been There, Done That: Meta-Learning with Episodic Recall](https://mlsanity.com/paper/1805.09692/) (2018)
- [Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences](https://mlsanity.com/paper/2509.16189/) (2025)
- [MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialogues](https://mlsanity.com/paper/2509.11860/) (2025)
- [Goal-Directed Search Outperforms Goal-Agnostic Memory Compression in Long-Context Memory Tasks](https://mlsanity.com/paper/2511.21726/) (2025)

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

- [MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents](https://mlsanity.com/paper/2605.18652/) (2026)
- [Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents](https://mlsanity.com/paper/2606.11680/) (2026)
- [When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers](https://mlsanity.com/paper/2607.00394/) (2026)
- [From Cognitive Architectures to Language Agents: A Mechanism-Level Review of Lineage, Convergence, and Migration Gaps](https://mlsanity.com/paper/2607.23942/) (2026)

## Abstract (arXiv)

External memory is a key component of modern large language model (LLM) systems, enabling long-term interaction and personalization. Despite its importance, memory management is still largely driven by hand-designed heuristics, offering little insight into the long-term and uncertain consequences of memory decisions. In practice, choices about what to read or write shape future retrieval and downstream behavior in ways that are difficult to anticipate. We argue that memory management should be viewed as a sequential decision-making problem under uncertainty, where the utility of memory is delayed and dependent on future interactions. To this end, we propose DAM (Decision-theoretic Agent Memory), a decision-theoretic framework that decomposes memory management into immediate information access and hierarchical storage maintenance. Within this architecture, candidate operations are evaluated via value functions and uncertainty estimators, enabling an aggregate policy to arbitrate decisions based on estimated long-term utility and risk. Our contribution is not a new algorithm, but a principled reframing that clarifies the limitations of heuristic approaches and provides a foundation for future research on uncertainty-aware memory systems.