mlsanityData to 7 Oct 2026

Can Past Experience Accelerate LLM Reasoning?

arXiv 2505.20643 ↗First posted 27 May 2025cs.LG cs.AIcited by 3

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Allocating more compute to large language models (LLMs) reasoning has generally been demonstrated to improve their effectiveness, but also results in increased inference time. In contrast, humans can perform tasks faster and better with increased experience and exposure. Hence, this paper aims to investigate the question: Can LLMs also become faster at reasoning through recurrent exposure on relevant tasks, and if so, how can it be achieved? To address these questions, we first formalize the problem setting of LLM reasoning speedup systematically in the dimensions of task relevancy and compute budget calculation. We then propose SpeedupLLM, a theoretically guaranteed framework to implement and benchmark such reasoning speedup behaviour based on adaptive compute allocation and memory mechanisms. We further conduct comprehensive experiments to benchmark such behaviour across different question similarity levels, memory methods, and reasoning methods. Results show that LLMs can generally reason faster with past experience, achieving up to a 56% reduction in compute cost when equipped with appropriate memory and reasoning methods.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 54 of its 76 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

54 of 76 references.

Closest ancestors · 17

Same direction, newest first

  1. 2025When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models2 Apr
  2. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models20 Mar
  3. 2025TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation6 Mar
  4. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning6 Mar
  5. 2025Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding3 Mar
  6. 2025How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach3 Mar
  7. 2025Self-Training Elicits Concise Reasoning in Large Language Models27 Feb
  8. 2025Dynamic Parallel Tree Search for Efficient LLM Reasoning22 Feb
  9. 2025Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights18 Feb
  10. 2025Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling10 Feb
  11. 2025s1: Simple test-time scaling31 Jan
  12. 2025O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning22 Jan
5 more
  1. 2025A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning5 Jan
  2. 2024Token-Budget-Aware LLM Reasoning24 Dec
  3. 2024Compressed Chain of Thought: Efficient Reasoning Through Dense Representations17 Dec
  4. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training29 Sep
  5. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing19 May

Other references · 37

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2024OpenAI o1 System Cardcited by 1,220
  6. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,193
  7. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 763
  8. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 622
  9. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  10. 2021Editing Factual Knowledge in Language Modelscited by 548
  11. 2021Fast Model Editing at Scalecited by 491
  12. 2025LIMO: Less is More for Reasoningcited by 488
25 more
  1. 2025The Lessons of Developing Process Reward Models in Mathematical Reasoningcited by 402
  2. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  3. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 335
  4. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  5. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 308
  6. 2025Chain of Draft: Thinking Faster by Writing Lesscited by 290
  7. 2024AlphaEdit: Null-Space Constrained Knowledge Editing for Language Modelscited by 224
  8. 2024When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Methodcited by 201
  9. 2023Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Controlcited by 180
  10. 2023HuaTuo: Tuning LLaMA Model with Chinese Medical Knowledgecited by 161
  11. 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 136
  12. 2023Recommender AI Agent: Integrating Large Language Models for Interactive Recommendationscited by 130
  13. 2024Fast Best-of-N Decoding via Speculative Rejectioncited by 112
  14. 2025SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMscited by 110
  15. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agentscited by 100
  16. 2023SCM: Enhancing Large Language Model with Self-Controlled Memory Frameworkcited by 98
  17. 2023InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuningcited by 80
  18. 2024GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Modelscited by 42
  19. 2024Self-Reflection in LLM Agents: Effects on Problem-Solving Performancecited by 38
  20. 2024On the Structural Memory of LLM Agentscited by 37
  21. 2024Uncovering Overfitting in Large Language Model Editingcited by 36
  22. 2024Online Adaptation of Language Models with a Memory of Amortized Contextscited by 35
  23. 2023Failures Pave the Way: Enhancing Large Language Models through Tuning-free Rule Accumulationcited by 30
  24. 2024Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuningcited by 20
  25. 2024RoT: Enhancing Large Language Models with Reflection on Search Treescited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memorycited by 16
  2. 2025Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoningcited by 4
  3. 2026Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Modelscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
  2. 2025Temporal Sampling for Forgotten Reasoning in LLMs
  3. 2024Inference Scaling vs Reasoning: An Empirical Analysis of Compute-Optimal LLM Problem-Solving
  4. 2026MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
  5. 2025Let's (not) just put things in Context: Test-Time Training for Long-Context LLMs
  6. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Models
  7. 2026Learning, Fast and Slow: Towards LLMs That Adapt Continually
  8. 2026ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning