# Beyond Static Summarization: Proactive Memory Extraction for LLM Agents

arXiv: https://arxiv.org/abs/2601.04463 · HTML: https://mlsanity.com/paper/2601.04463/

## Key facts

- Cited by 21 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 18 of its 42 references that are in the map.
- First posted on arXiv 8 Jan 2026.

## Placed in

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

## Builds on (most cited first, 18 of 18)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [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)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT](https://mlsanity.com/paper/2302.10205/) (2023)
- [Unified Structure Generation for Universal Information Extraction](https://mlsanity.com/paper/2203.12277/) (2022)
- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [Portuguese Named Entity Recognition using BERT-CRF](https://mlsanity.com/paper/1909.10649/) (2019)
- [Dr.ICL: Demonstration-Retrieved In-context Learning](https://mlsanity.com/paper/2305.14128/) (2023)
- [AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents](https://mlsanity.com/paper/2512.23343/) (2025)
- [Human Learning by Model Feedback: The Dynamics of Iterative Prompting with Midjourney](https://mlsanity.com/paper/2311.12131/) (2023)

## Built on by (most cited first, 21 of 21)

- [SkillX: Automatically Constructing Skill Knowledge Bases for Agents](https://mlsanity.com/paper/2604.04804/) (2026)
- [Graph-based Agent Memory: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2602.05665/) (2026)
- [Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations](https://mlsanity.com/paper/2602.19320/) (2026)
- [ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents](https://mlsanity.com/paper/2603.00026/) (2026)
- [EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents](https://mlsanity.com/paper/2606.05894/) (2026)
- [Mitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory Representation](https://mlsanity.com/paper/2605.25869/) (2026)
- [Scaling Self-Evolving Agents via Parametric Memory](https://mlsanity.com/paper/2606.04536/) (2026)
- [HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling](https://mlsanity.com/paper/2602.13933/) (2026)
- [Mem-π: Adaptive Memory through Learning When and What to Generate](https://mlsanity.com/paper/2605.21463/) (2026)
- [Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents](https://mlsanity.com/paper/2606.11680/) (2026)
- [MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents](https://mlsanity.com/paper/2605.03675/) (2026)
- [Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents](https://mlsanity.com/paper/2607.20972/) (2026)
- [Agents in the Large: Perception-Centered Architecture for Persistent Agents](https://mlsanity.com/paper/2608.30478/) (2026)
- [Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs](https://mlsanity.com/paper/2606.09038/) (2026)
- [MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale](https://mlsanity.com/paper/2608.02613/) (2026)
- [Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization](https://mlsanity.com/paper/2608.09043/) (2026)
- [Toward Effective and Reliable LLM Agents via Dynamic Ontology](https://mlsanity.com/paper/2608.22974/) (2026)
- [When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression](https://mlsanity.com/paper/2609.29875/) (2026)
- [NLPG: Natural-Language Policy Gradients for Self-Evolving Language Agents](https://mlsanity.com/paper/2609.33379/) (2026)
- [Grounding Memory Summarization in Utility Intent](https://mlsanity.com/paper/2609.33417/) (2026)
- [Remember Before You're Asked: MemDream for Self-Probing Memory Evolution](https://mlsanity.com/paper/2609.34545/) (2026)

## Abstract (arXiv)

Memory management is vital for LLM agents in long-term and personalized interactions. Most previous work studies how to retrieve and use memory, but pays less attention to how memory is extracted. We find two main limitations in existing methods. First, extraction is "ahead-of-time": the agent saves information before it knows future tasks. A single summary prompt often mixes details, events, and relations, so useful information is lost. Second, extraction is usually one-off. Without verification, errors and hallucinations may stay in memory for a long time. To address these limitations, we propose ProMem, a proactive memory extraction framework. It separates details, events, and relations, and uses different extraction strategies for each type. It also checks completeness to recover missed events and verifies facts at the atomic level to reduce hallucinations. Experiments show that ProMem improves memory completeness and QA accuracy, while keeping a good balance between quality and token cost.