# Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents

arXiv: https://arxiv.org/abs/2509.23040 · HTML: https://mlsanity.com/paper/2509.23040/

## Key facts

- Cited by 38 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 36 of its 51 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 30 of 36)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [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)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent](https://mlsanity.com/paper/2507.02259/) (2025)
- [REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization](https://mlsanity.com/paper/2501.03262/) (2025)
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [LongNet: Scaling Transformers to 1,000,000,000 Tokens](https://mlsanity.com/paper/2307.02486/) (2023)
- [Qwen2.5-1M Technical Report](https://mlsanity.com/paper/2501.15383/) (2025)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)

## Built on by (most cited first, 30 of 38)

- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents](https://mlsanity.com/paper/2602.01869/) (2026)
- [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (2026)
- [RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction](https://mlsanity.com/paper/2601.06966/) (2026)
- [Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding](https://mlsanity.com/paper/2511.22850/) (2025)
- [MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning](https://mlsanity.com/paper/2601.21468/) (2026)
- [PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments](https://mlsanity.com/paper/2603.23231/) (2026)
- [SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent](https://mlsanity.com/paper/2605.24468/) (2026)
- [When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning](https://mlsanity.com/paper/2602.10560/) (2026)
- [Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning](https://mlsanity.com/paper/2602.18493/) (2026)
- [Memory Intelligence Agent](https://mlsanity.com/paper/2604.04503/) (2026)
- [Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments](https://mlsanity.com/paper/2605.27209/) (2026)
- [EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents](https://mlsanity.com/paper/2606.05894/) (2026)
- [TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory](https://mlsanity.com/paper/2606.25161/) (2026)
- [Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMs](https://mlsanity.com/paper/2512.06258/) (2025)
- [KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning](https://mlsanity.com/paper/2602.23592/) (2026)
- [CoMem: Context Management with A Decoupled Long-Context Model](https://mlsanity.com/paper/2605.30842/) (2026)
- [MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue](https://mlsanity.com/paper/2603.06194/) (2026)
- [MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning](https://mlsanity.com/paper/2605.13037/) (2026)
- [MiA-Signature: Approximating Global Activation for Long-Context Understanding](https://mlsanity.com/paper/2605.06416/) (2026)
- [Cyclical Entropy Eruption: Entropy Dynamics in Agent Reinforcement Learning](https://mlsanity.com/paper/2605.27954/) (2026)
- [InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain](https://mlsanity.com/paper/2606.03329/) (2026)
- [World-Model Collapse as a Phase Transition](https://mlsanity.com/paper/2606.31399/) (2026)
- [FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents](https://mlsanity.com/paper/2606.31522/) (2026)
- [TransMem: Transforming Hidden States into Memory for Large Language Models](https://mlsanity.com/paper/2607.29032/) (2026)
- [MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading](https://mlsanity.com/paper/2605.10268/) (2026)
- [On Problems of Implicit Context Compression for Software Engineering Agents](https://mlsanity.com/paper/2605.11051/) (2026)
- [MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generation](https://mlsanity.com/paper/2605.17640/) (2026)
- [PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative Memory](https://mlsanity.com/paper/2608.03048/) (2026)
- [Towards a Formal Definition of Agent Memory: Basis, Span, Optimality, and the Sequential Memory Problem](https://mlsanity.com/paper/2608.11654/) (2026)

## Abstract (arXiv)

Large language models face challenges in long-context question answering, where key evidence of a query may be dispersed across millions of tokens. Existing works equip large language models with a memory buffer that is dynamically updated via a linear document scan, also known as the "memorize while reading" methods. While this approach scales efficiently, it suffers from pruning of latent evidence, information loss through overwriting, and sparse reinforcement learning signals. To tackle these challenges, we present ReMemR1, which integrates the mechanism of memory retrieval into the memory update process, enabling the agent to selectively callback historical memories for non-linear reasoning. To further strengthen training, we propose a multi-level reward design, which combines final-answer rewards with dense, step-level signals that guide effective memory use. Together, these contributions mitigate information degradation, improve supervision, and support complex multi-hop reasoning. Extensive experiments demonstrate that ReMemR1 significantly outperforms state-of-the-art baselines on long-context question answering while incurring negligible computational overhead, validating its ability to trade marginal cost for robust long-context reasoning.