# Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks

arXiv: https://arxiv.org/abs/2510.12635 · HTML: https://mlsanity.com/paper/2510.12635/

## Key facts

- Cited by 66 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 24 of its 31 references that are in the map.
- First posted on arXiv 14 Oct 2025.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [YaRN: Efficient Context Window Extension of Large Language Models](https://mlsanity.com/paper/2309.00071/) (2023)
- [MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent](https://mlsanity.com/paper/2507.02259/) (2025)
- [MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents](https://mlsanity.com/paper/2506.15841/) (2025)
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation](https://mlsanity.com/paper/2409.12941/) (2024)
- [Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL](https://mlsanity.com/paper/2508.07976/) (2025)
- [ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization](https://mlsanity.com/paper/2509.13313/) (2025)
- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management](https://mlsanity.com/paper/2510.06727/) (2025)
- [Hierarchical Document Refinement for Long-context Retrieval-augmented Generation](https://mlsanity.com/paper/2505.10413/) (2025)

## Built on by (most cited first, 30 of 66)

- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents](https://mlsanity.com/paper/2601.01885/) (2026)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [SkillOS: Learning Skill Curation for Self-Evolving Agents](https://mlsanity.com/paper/2605.06614/) (2026)
- [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (2026)
- [Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations](https://mlsanity.com/paper/2602.19320/) (2026)
- [From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms](https://mlsanity.com/paper/2605.06716/) (2026)
- [Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Framework](https://mlsanity.com/paper/2603.11768/) (2026)
- [MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systems](https://mlsanity.com/paper/2605.25002/) (2026)
- [JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution](https://mlsanity.com/paper/2608.25593/) (2026)
- [AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation](https://mlsanity.com/paper/2601.08323/) (2026)
- [Learning Agent-Compatible Context Management for Long-Horizon Tasks](https://mlsanity.com/paper/2605.30785/) (2026)
- [PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments](https://mlsanity.com/paper/2603.23231/) (2026)
- [ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents](https://mlsanity.com/paper/2604.01664/) (2026)
- [AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents](https://mlsanity.com/paper/2512.23343/) (2025)
- [Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents](https://mlsanity.com/paper/2607.08716/) (2026)
- [Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty](https://mlsanity.com/paper/2605.11436/) (2026)
- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI](https://mlsanity.com/paper/2510.16720/) (2025)
- [Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory](https://mlsanity.com/paper/2605.10870/) (2026)
- [Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents](https://mlsanity.com/paper/2607.13591/) (2026)
- [An Empirical Study of Harness Design for Coding Agents](https://mlsanity.com/paper/2609.20804/) (2026)
- [Aligning Agentic World Models via Knowledgeable Experience Learning](https://mlsanity.com/paper/2601.13247/) (2026)
- [Large Language Model Agents Are Not Always Faithful Self-Evolvers](https://mlsanity.com/paper/2601.22436/) (2026)
- [MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs](https://mlsanity.com/paper/2605.08374/) (2026)
- [AutoMem: Automated Learning of Memory as a Cognitive Skill](https://mlsanity.com/paper/2607.01224/) (2026)
- [Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation](https://mlsanity.com/paper/2607.05377/) (2026)
- [AREX: Towards a Recursively Self-Improving Agent for Deep Research](https://mlsanity.com/paper/2607.21461/) (2026)
- [See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoning](https://mlsanity.com/paper/2603.23864/) (2026)
- [MemFactory: Unified Inference & Training Framework for Agent Memory](https://mlsanity.com/paper/2603.29493/) (2026)

## Abstract (arXiv)

Long-context Large Language Models, despite their expanded capacity, require careful working memory management to mitigate attention dilution during long-horizon tasks. Yet existing approaches rely on external mechanisms that lack awareness of the agent's reasoning state, leading to suboptimal decisions. We propose Memory-as-Action (MemAct), a framework that treats working memory management as learnable policy actions. By formulating context management as in-place editing operations (deletion, insertion), MemAct enables joint optimization of information retention and task performance through end-to-end reinforcement learning. To address the computational challenges of dynamic context updates, we introduce Dynamic Context Policy Optimization, which restores training efficiency without compromising reasoning integrity. Experiments show that MemAct-RL-14B matches the accuracy of models 16× larger while reducing average context length by 51%, with learned strategies that adapt to model capabilities and generalize across task complexities.