# MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning

arXiv: https://arxiv.org/abs/2511.02805 · HTML: https://mlsanity.com/paper/2511.02805/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 65 of its 74 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 30 of 65)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [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)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [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)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [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)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)

## Built on by (most cited first, 27 of 27)

- [Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation](https://mlsanity.com/paper/2605.18740/) (2026)
- [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (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)
- [Mem-T: Densifying Rewards for Long-Horizon Memory Agents](https://mlsanity.com/paper/2601.23014/) (2026)
- [DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation](https://mlsanity.com/paper/2602.22839/) (2026)
- [PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments](https://mlsanity.com/paper/2603.23231/) (2026)
- [AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents](https://mlsanity.com/paper/2512.23343/) (2025)
- [Beyond Monolithic Architectures: A Multi-Agent Search and Knowledge Optimization Framework for Agentic Search](https://mlsanity.com/paper/2601.04703/) (2026)
- [EvoIdeator: Evolving Scientific Ideas through Checklist-Grounded Reinforcement Learning](https://mlsanity.com/paper/2603.21728/) (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)
- [GUI Agents with Reinforcement Learning: Toward Digital Inhabitants](https://mlsanity.com/paper/2604.27955/) (2026)
- [Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents](https://mlsanity.com/paper/2606.11680/) (2026)
- [Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory](https://mlsanity.com/paper/2605.00702/) (2026)
- [AWM: Answerable Working Memory for Long-Document VQA Agents](https://mlsanity.com/paper/2608.25618/) (2026)
- [APEx: Distillation of Agent Procedural Experience for Adaptive Deep Research Question Answering](https://mlsanity.com/paper/2609.02253/) (2026)
- [Plan Before Search: Search Agents Need Plan](https://mlsanity.com/paper/2605.28354/) (2026)
- [Dense Process Supervision for Search Agents via Fact Utility Estimation](https://mlsanity.com/paper/2609.00833/) (2026)
- [MemTrain: Self-Supervised Context Memory Training](https://mlsanity.com/paper/2606.03197/) (2026)
- [R2-Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search](https://mlsanity.com/paper/2606.28566/) (2026)
- [Multi-Head Recurrent Memory Agents](https://mlsanity.com/paper/2607.01523/) (2026)
- [Mint-Agent: Introducing Finance-Native Agentic Foundation Models](https://mlsanity.com/paper/2608.16386/) (2026)
- [Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents](https://mlsanity.com/paper/2609.27334/) (2026)
- [Remember Before You're Asked: MemDream for Self-Probing Memory Evolution](https://mlsanity.com/paper/2609.34545/) (2026)
- [LatentHarness: Learning Latent Actions for Memory and Reasoning via Counterfactual Policy Distillation](https://mlsanity.com/paper/2609.39740/) (2026)
- [AMBER: Training Long-Horizon Web Agents through Append-Only Memory](https://mlsanity.com/paper/2610.07118/) (2026)

## Abstract (arXiv)

LLM-based search agents often concatenate the full interaction history into the context, producing long and noisy inputs, and increasing compute cost and GPU memory overhead. To address this issue, we propose MemSearcher, an agent framework that maintains a compact memory during multi-turn interactions, retaining only question-relevant information and thereby keeping the context length stable across turns. Training MemSearcher is challenging because each trajectory spans multiple turns under different LLM contexts, making each turn an independent optimization target in reinforcement learning. We introduce multi-context GRPO, which propagates trajectory-level advantages to all turns for end-to-end optimization. Experiments demonstrate that MemSearcher outperforms strong history-concatenation (ReAct-style) baselines on a range of public datasets while maintaining nearly constant token counts across multi-turn interactions. The code and models will be publicly available at https://github.com/icip-cas/MemSearcher