# ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory

arXiv: https://arxiv.org/abs/2509.04439 · HTML: https://mlsanity.com/paper/2509.04439/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 28 of its 35 references that are in the map.
- First posted on arXiv 4 Sep 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 28 of 28)

- [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)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [ERNIE: Enhanced Language Representation with Informative Entities](https://mlsanity.com/paper/1905.07129/) (2019)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [Memorizing Transformers](https://mlsanity.com/paper/2203.08913/) (2022)
- [Recurrent Memory Transformer](https://mlsanity.com/paper/2207.06881/) (2022)
- [Hierarchical Reasoning Model](https://mlsanity.com/paper/2506.21734/) (2025)
- [A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence](https://mlsanity.com/paper/2507.21046/) (2025)
- [Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory](https://mlsanity.com/paper/2504.07952/) (2025)
- [On the Measure of Intelligence](https://mlsanity.com/paper/1911.01547/) (2019)
- [Hypothesis Search: Inductive Reasoning with Language Models](https://mlsanity.com/paper/2309.05660/) (2023)
- [HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model](https://mlsanity.com/paper/2408.09559/) (2024)
- [The Surprising Effectiveness of Test-Time Training for Few-Shot Learning](https://mlsanity.com/paper/2411.07279/) (2024)
- [Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models](https://mlsanity.com/paper/2406.04271/) (2024)
- [Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement](https://mlsanity.com/paper/2310.08559/) (2023)
- [Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory](https://mlsanity.com/paper/2311.08719/) (2023)
- [Combining Induction and Transduction for Abstract Reasoning](https://mlsanity.com/paper/2411.02272/) (2024)
- [Contextual Experience Replay for Self-Improvement of Language Agents](https://mlsanity.com/paper/2506.06698/) (2025)
- [Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI](https://mlsanity.com/paper/2507.14172/) (2025)
- [MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory](https://mlsanity.com/paper/2404.11672/) (2024)
- [CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memory](https://mlsanity.com/paper/2402.13449/) (2024)

## Built on by (most cited first, 24 of 24)

- [SkillOS: Learning Skill Curation for Self-Evolving Agents](https://mlsanity.com/paper/2605.06614/) (2026)
- [KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems](https://mlsanity.com/paper/2510.12872/) (2025)
- [TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models](https://mlsanity.com/paper/2601.18744/) (2026)
- [TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning](https://mlsanity.com/paper/2510.03519/) (2025)
- [SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds](https://mlsanity.com/paper/2512.01078/) (2025)
- [QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation](https://mlsanity.com/paper/2512.19134/) (2025)
- [Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL](https://mlsanity.com/paper/2602.03773/) (2026)
- [PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning](https://mlsanity.com/paper/2607.20064/) (2026)
- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [MultiSessionCollab: Learning User Preferences with Memory to Improve Long-Term Collaboration](https://mlsanity.com/paper/2601.02702/) (2026)
- [Workspace Optimization: How to Train Your Agent](https://mlsanity.com/paper/2605.09650/) (2026)
- [Think Visually, Reason Textually: Vision-Language Synergy in ARC](https://mlsanity.com/paper/2511.15703/) (2025)
- [The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning](https://mlsanity.com/paper/2603.13372/) (2026)
- [HIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answering](https://mlsanity.com/paper/2602.15513/) (2026)
- [Test-Time Learning with an Evolving Library](https://mlsanity.com/paper/2605.14477/) (2026)
- [FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse](https://mlsanity.com/paper/2606.11290/) (2026)
- [TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning](https://mlsanity.com/paper/2607.08940/) (2026)
- [HiNS: Hierarchical Negative Sampling for More Comprehensive Memory Retrieval Embedding Model](https://mlsanity.com/paper/2601.14857/) (2026)
- [AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Composition](https://mlsanity.com/paper/2606.14674/) (2026)
- [The Past Is Prologue: A Plug-in Controller for Selective Updates in Sequentially Evolving LLM Memory](https://mlsanity.com/paper/2606.31121/) (2026)
- [MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning](https://mlsanity.com/paper/2607.06974/) (2026)
- [Fine-Tuning Small Language Models for Solution-Oriented Windows Event Log Analysis](https://mlsanity.com/paper/2605.06330/) (2026)
- [Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory](https://mlsanity.com/paper/2605.15384/) (2026)
- [LS-AR: Future-Predictive Latent Steering in Autoregressive LLMs](https://mlsanity.com/paper/2610.03093/) (2026)

## Abstract (arXiv)

While inference-time scaling enables LLMs to carry out increasingly long and capable reasoning traces, the patterns and insights uncovered during these traces are immediately discarded once the context window is reset for a new query. External memory is a natural way to persist these discoveries, and recent work has shown clear benefits for reasoning-intensive tasks. We see an opportunity to make such memories more broadly reusable and scalable by moving beyond instance-based memory entries (e.g. exact query/response pairs, or summaries tightly coupled with the original problem context) toward concept-level memory: reusable, modular abstractions distilled from solution traces and stored in natural language. For future queries, relevant concepts are selectively retrieved and integrated into the prompt, enabling test-time continual learning without weight updates. Our design introduces new strategies for abstracting takeaways from rollouts and retrieving entries for new queries, promoting reuse and allowing memory to expand with additional experiences. We evaluate on ARC-AGI, a benchmark that stresses compositional generalization and abstract reasoning, making it a natural fit for concept memory. Our method yields a 7.5% relative gain over a strong no-memory baseline with performance continuing to scale with inference compute. We find abstract concepts to be the most consistent memory design, outscoring the baseline at all tested inference compute scales. Moreover, dynamically updating memory during test-time outperforms fixed settings, supporting the hypothesis that accumulating and abstracting patterns enables further solutions in a form of self-improvement. Code is available at https://github.com/matt-seb-ho/arc_memo.