# Disentangling Memory and Reasoning Ability in Large Language Models

arXiv: https://arxiv.org/abs/2411.13504 · HTML: https://mlsanity.com/paper/2411.13504/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 38 of its 51 references that are in the map.
- First posted on arXiv 20 Nov 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 38)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective](https://mlsanity.com/paper/2305.15408/) (2023)
- [Physics of Language Models: Part 3.1, Knowledge Storage and Extraction](https://mlsanity.com/paper/2309.14316/) (2023)
- [Think before you speak: Training Language Models With Pause Tokens](https://mlsanity.com/paper/2310.02226/) (2023)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity](https://mlsanity.com/paper/2310.07521/) (2023)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Do Large Language Models Latently Perform Multi-Hop Reasoning?](https://mlsanity.com/paper/2402.16837/) (2024)
- [Distilling System 2 into System 1](https://mlsanity.com/paper/2407.06023/) (2024)
- [The Impact of Reasoning Step Length on Large Language Models](https://mlsanity.com/paper/2401.04925/) (2024)
- [Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models](https://mlsanity.com/paper/2402.14848/) (2024)
- [Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse](https://mlsanity.com/paper/2410.21333/) (2024)
- [Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization](https://mlsanity.com/paper/2405.15071/) (2024)
- [Thread of Thought Unraveling Chaotic Contexts](https://mlsanity.com/paper/2311.08734/) (2023)
- [Guiding Language Model Reasoning with Planning Tokens](https://mlsanity.com/paper/2310.05707/) (2023)
- [Visual Agents as Fast and Slow Thinkers](https://mlsanity.com/paper/2408.08862/) (2024)
- [Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory](https://mlsanity.com/paper/1809.05296/) (2018)
- [Understanding and Patching Compositional Reasoning in LLMs](https://mlsanity.com/paper/2402.14328/) (2024)
- [Enhancing Zero-Shot Chain-of-Thought Reasoning in Large Language Models through Logic](https://mlsanity.com/paper/2309.13339/) (2023)
- [Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?](https://mlsanity.com/paper/2311.09702/) (2023)

## Built on by (most cited first, 30 of 44)

- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [Efficient Reasoning Models: A Survey](https://mlsanity.com/paper/2504.10903/) (2025)
- [A Survey on Latent Reasoning](https://mlsanity.com/paper/2507.06203/) (2025)
- [Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2602.22817/) (2026)
- [Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding](https://mlsanity.com/paper/2502.01563/) (2025)
- [Implicit Reasoning in Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2509.02350/) (2025)
- [Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics](https://mlsanity.com/paper/2505.00675/) (2025)
- [LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning](https://mlsanity.com/paper/2510.04573/) (2025)
- [MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning](https://mlsanity.com/paper/2511.02805/) (2025)
- [Disentangling Reasoning and Knowledge in Medical Large Language Models](https://mlsanity.com/paper/2505.11462/) (2025)
- [Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models](https://mlsanity.com/paper/2504.19373/) (2025)
- [According to Me: Long-Term Personalized Referential Memory QA](https://mlsanity.com/paper/2603.01990/) (2026)
- [Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMs](https://mlsanity.com/paper/2412.14368/) (2024)
- [General Intelligence Requires Reward-based Pretraining](https://mlsanity.com/paper/2502.19402/) (2025)
- [UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models](https://mlsanity.com/paper/2505.20154/) (2025)
- [LoopMoE: Unifying Iterative Computation with Mixture-of-Experts for Language Modeling](https://mlsanity.com/paper/2606.04438/) (2026)
- [Re-Imagining Multimodal Instruction Tuning: A Representation View](https://mlsanity.com/paper/2503.00723/) (2025)
- [Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies](https://mlsanity.com/paper/2512.01970/) (2025)
- [LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning](https://mlsanity.com/paper/2602.01705/) (2026)
- [SeLaR: Selective Latent Reasoning in Large Language Models](https://mlsanity.com/paper/2604.08299/) (2026)
- [Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time](https://mlsanity.com/paper/2508.02037/) (2025)
- [Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning](https://mlsanity.com/paper/2508.19202/) (2025)
- [Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation](https://mlsanity.com/paper/2505.03320/) (2025)
- [Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations](https://mlsanity.com/paper/2510.00496/) (2025)
- [Skill-RAG: Failure-State-Aware Retrieval Augmentation via Hidden-State Probing and Skill Routing](https://mlsanity.com/paper/2604.15771/) (2026)
- [Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents](https://mlsanity.com/paper/2606.11680/) (2026)
- [Large Language Models Could Be Rote Learners](https://mlsanity.com/paper/2504.08300/) (2025)
- [Honey, I Shrunk the Language Model: Impact of Knowledge Distillation Methods on Performance and Explainability](https://mlsanity.com/paper/2504.16056/) (2025)
- [Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency](https://mlsanity.com/paper/2601.05905/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated strong performance in handling complex tasks requiring both extensive knowledge and reasoning abilities. However, the existing LLM inference pipeline operates as an opaque process without explicit separation between knowledge retrieval and reasoning steps, making the model's decision-making process unclear and disorganized. This ambiguity can lead to issues such as hallucinations and knowledge forgetting, which significantly impact the reliability of LLMs in high-stakes domains. In this paper, we propose a new inference paradigm that decomposes the complex inference process into two distinct and clear actions: (1) memory recall: which retrieves relevant knowledge, and (2) reasoning: which performs logical steps based on the recalled knowledge. To facilitate this decomposition, we introduce two special tokens memory and reason, guiding the model to distinguish between steps that require knowledge retrieval and those that involve reasoning. Our experiment results show that this decomposition not only improves model performance but also enhances the interpretability of the inference process, enabling users to identify sources of error and refine model responses effectively. The code is available at https://github.com/MingyuJ666/Disentangling-Memory-and-Reasoning.