# MoT: Memory-of-Thought Enables ChatGPT to Self-Improve

arXiv: https://arxiv.org/abs/2305.05181 · HTML: https://mlsanity.com/paper/2305.05181/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 48 of its 80 references that are in the map.
- First posted on arXiv 9 May 2023.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)
- Synthetic data and self-improvement for LLMs / [Synthetic reasoning data and bootstrapping](https://mlsanity.com/synth/synthetic-reasoning-data-and-bootstrapping/)

## Builds on (most cited first, 30 of 48)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022)
- [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023)
- [Pre-trained Models for Natural Language Processing: A Survey](https://mlsanity.com/paper/2003.08271/) (2020)
- [Augmented Language Models: a Survey](https://mlsanity.com/paper/2302.07842/) (2023)
- [Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor](https://mlsanity.com/paper/2212.09689/) (2022)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [Large Language Models Are Reasoning Teachers](https://mlsanity.com/paper/2212.10071/) (2022)
- [Large Language Models are Better Reasoners with Self-Verification](https://mlsanity.com/paper/2212.09561/) (2022)

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

- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [LLM Multi-Agent Systems: Challenges and Open Problems](https://mlsanity.com/paper/2402.03578/) (2024)
- [Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey](https://mlsanity.com/paper/2311.07914/) (2023)
- [A Survey on Self-Evolution of Large Language Models](https://mlsanity.com/paper/2404.14387/) (2024)
- [Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication](https://mlsanity.com/paper/2312.01823/) (2023)
- [Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs](https://mlsanity.com/paper/2410.23875/) (2024)
- [StreamBench: Towards Benchmarking Continuous Improvement of Language Agents](https://mlsanity.com/paper/2406.08747/) (2024)
- [Large Language Models for Planning: A Comprehensive and Systematic Survey](https://mlsanity.com/paper/2505.19683/) (2025)
- [What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration](https://mlsanity.com/paper/2410.20482/) (2024)
- [On Safety Risks in Experience-Driven Self-Evolving Agents](https://mlsanity.com/paper/2604.16968/) (2026)
- [Unearthing Large Scale Domain-Specific Knowledge from Public Corpora](https://mlsanity.com/paper/2401.14624/) (2024)
- [Importance Weighting Can Help Large Language Models Self-Improve](https://mlsanity.com/paper/2408.09849/) (2024)
- [Self-Evolving GPT: A Lifelong Autonomous Experiential Learner](https://mlsanity.com/paper/2407.08937/) (2024)
- [HiMA-Ecom: Enabling Joint Training of Hierarchical Multi-Agent E-commerce Assistants](https://mlsanity.com/paper/2506.19846/) (2025)
- [Scaling Laws for Many-Shot In-Context Learning with Self-Generated Annotations](https://mlsanity.com/paper/2503.03062/) (2025)
- [Multi-Agent LLM Judge: automatic personalized LLM judge design for evaluating natural language generation applications](https://mlsanity.com/paper/2504.02867/) (2025)
- [Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey](https://mlsanity.com/paper/2505.03418/) (2025)
- [Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks](https://mlsanity.com/paper/2505.19806/) (2025)
- [Formalizing the Safety, Security, and Functional Properties of Agentic AI Systems](https://mlsanity.com/paper/2510.14133/) (2025)
- [Large Language Model Agents Are Not Always Faithful Self-Evolvers](https://mlsanity.com/paper/2601.22436/) (2026)
- [ONSEP: A Novel Online Neural-Symbolic Framework for Event Prediction Based on Large Language Model](https://mlsanity.com/paper/2408.07840/) (2024)
- [Zero-to-Strong Generalization: Eliciting Strong Capabilities of Large Language Models Iteratively without Gold Labels](https://mlsanity.com/paper/2409.12425/) (2024)
- [Deploying Foundation Model Powered Agent Services: A Survey](https://mlsanity.com/paper/2412.13437/) (2024)
- [CDW-CoT: Clustered Distance-Weighted Chain-of-Thoughts Reasoning](https://mlsanity.com/paper/2501.12226/) (2025)
- [CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs](https://mlsanity.com/paper/2601.11047/) (2026)
- [PICLe: Pseudo-Annotations for In-Context Learning in Low-Resource Named Entity Detection](https://mlsanity.com/paper/2412.11923/) (2024)
- [Fine-Grained Emotion Recognition via In-Context Learning](https://mlsanity.com/paper/2510.06600/) (2025)
- [Making Large Language Models Better Reasoners with Orchestrated Streaming Experiences](https://mlsanity.com/paper/2504.00473/) (2025)
- [Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknesses](https://mlsanity.com/paper/2508.05009/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) have shown impressive abilities in various tasks. However, fundamentally improving them depends on high-quality datasets or computationally expensive fine-tuning. On the contrary, humans can easily improve themselves by self-thinking and memory, without external resources. In this paper, we propose a framework, MoT, to let the LLM self-improve through Memory-of-Thought, without annotated datasets and parameter updates. Specifically, MoT is divided into two stages: 1. before the test stage, the LLM pre-thinks on the unlabeled dataset and saves the high-confidence thoughts as external memory; 2. During the test stage, given a test question, the LLM recalls relevant memory to help itself reason and answer it. Experimental results show that MoT can help ChatGPT significantly improve its abilities in arithmetic reasoning, commonsense reasoning, factual reasoning, and natural language inference. Further analyses show that each component contributes critically to the improvements and MoT can lead to consistent improvements across various CoT methods and LLMs.