# Evaluating Long-Term Memory for Long-Context Question Answering

arXiv: https://arxiv.org/abs/2510.23730 · HTML: https://mlsanity.com/paper/2510.23730/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Builds on (most cited first, 17 of 17)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [Reliable, Adaptable, and Attributable Language Models with Retrieval](https://mlsanity.com/paper/2403.03187/) (2024)
- [RET-LLM: Towards a General Read-Write Memory for Large Language Models](https://mlsanity.com/paper/2305.14322/) (2023)
- [Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory](https://mlsanity.com/paper/2311.08719/) (2023)
- [TRAM: Benchmarking Temporal Reasoning for Large Language Models](https://mlsanity.com/paper/2310.00835/) (2023)
- [Imagining and building wise machines: The centrality of AI metacognition](https://mlsanity.com/paper/2411.02478/) (2024)
- [Survey on Memory-Augmented Neural Networks: Cognitive Insights to AI Applications](https://mlsanity.com/paper/2312.06141/) (2023)

## Built on by (most cited first, 8 of 8)

- [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (2026)
- [MemVerse: Multimodal Memory for Lifelong Learning Agents](https://mlsanity.com/paper/2512.03627/) (2025)
- [Gated Differentiable Working Memory for Long-Context Language Modeling](https://mlsanity.com/paper/2601.12906/) (2026)
- [Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents](https://mlsanity.com/paper/2604.22085/) (2026)
- [MemCoT: Test-Time Scaling through Memory-Driven Chain-of-Thought](https://mlsanity.com/paper/2604.08216/) (2026)
- [Towards a Formal Definition of Agent Memory: Basis, Span, Optimality, and the Sequential Memory Problem](https://mlsanity.com/paper/2608.11654/) (2026)
- [MSM-Mem: A Universal Medical Structured Multimodal Memory Framework for Medical AI Agents](https://mlsanity.com/paper/2608.21810/) (2026)
- [Can LLMs Reason Over Long Horizons? An Empirical Evaluation of Context Strategies for Longitudinal Clinical Reasoning](https://mlsanity.com/paper/2610.00562/) (2026)

## Abstract (arXiv)

In order for large language models to achieve true conversational continuity and benefit from experiential learning, they need memory. While research has focused on the development of complex memory systems, it remains unclear which types of memory are most effective for long-context conversational tasks. We present a systematic evaluation of memory-augmented methods on long-context dialogues annotated for question-answering tasks that require diverse reasoning strategies. We analyse full-context prompting, semantic memory through retrieval-augmented generation and agentic memory, episodic memory through in-context learning, and procedural memory through prompt optimization. Our findings show that memory-augmented approaches reduce token usage by over 90% while maintaining competitive accuracy. Memory architecture complexity should scale with model capability, with foundation models benefitting most from RAG, and stronger instruction-tuned models gaining from episodic learning through reflections and more complex agentic semantic memory. In particular, episodic memory can help LLMs recognise the limits of their own knowledge.