mlsanityData to 7 Oct 2026

Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models

arXiv 2501.02026 ↗First posted 3 Jan 2025cs.CL cs.AI cs.LGcited by 3

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

Abstract (arXiv)

Enhancing the reasoning capabilities of Large Language Models remains a critical challenge in artificial intelligence. We introduce RDoLT, Recursive Decomposition of Logical Thought prompting, a novel framework that significantly boosts LLM reasoning performance. RDoLT is built on three key innovations: (1) recursively breaking down complex reasoning tasks into sub-tasks of progressive complexity; (2) employing an advanced selection and scoring mechanism to identify the most promising reasoning thoughts; and (3) integrating a knowledge propagation module that mimics human learning by keeping track of strong and weak thoughts for information propagation. Our approach was evaluated across multiple benchmarks, including GSM8K, SVAMP, MultiArith, LastLetterConcatenation, and Gaokao2023 Math. The results demonstrate that RDoLT consistently outperforms existing state-of-the-art techniques, achieving a 90.98 percent accuracy on GSM8K with ChatGPT-4, surpassing state-of-the-art techniques by 6.28 percent. Similar improvements were observed on other benchmarks, with accuracy gains ranging from 5.5 percent to 6.75 percent. These findings highlight RDoLT's potential to advance prompt engineering, offering a more effective and generalizable approach to complex reasoning tasks.

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 41 of its 67 references that are in the map. First posted on arXiv 3 Jan 2025.

Builds on

41 of 67 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Large Language Models Cannot Self-Correct Reasoning Yet3 Oct
  2. 2023Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models20 Aug
  3. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Models17 May
  4. 2023Self-Evaluation Guided Beam Search for Reasoning1 May
  5. 2023REFINER: Reasoning Feedback on Intermediate Representations4 Apr
  6. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar

Other references · 35

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  7. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  8. 2024Qwen2 Technical Reportcited by 2,076
  9. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  10. 2023Teaching Large Language Models to Self-Debugcited by 963
  11. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  12. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
23 more
  1. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 317
  2. 2022Generating Sequences by Learning to Self-Correctcited by 271
  3. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 221
  4. 2022Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionalscited by 191
  5. 2024MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoningcited by 145
  6. 2024Chain of Thoughtlessness? An Analysis of CoT in Planningcited by 100
  7. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agentcited by 92
  8. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  9. 2023Large Language Models Are Not Strong Abstract Reasonerscited by 52
  10. 2024A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Modelscited by 52
  11. 2024A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Taskscited by 46
  12. 2022Rainier: Reinforced Knowledge Introspector for Commonsense Question Answeringcited by 43
  13. 2021Learning to Repair: Repairing model output errors after deployment using a dynamic memory of feedbackcited by 35
  14. 2021NL-EDIT: Correcting semantic parse errors through natural language interactioncited by 33
  15. 2024MLDT: Multi-Level Decomposition for Complex Long-Horizon Robotic Task Planning with Open-Source Large Language Modelcited by 15
  16. 2023User Interaction Patterns and Breakdowns in Conversing with LLM-Powered Voice Assistantscited by 14
  17. 2024Machine Translation with Large Language Models: Prompt Engineering for Persian, English, and Russian Directionscited by 12
  18. 2024Large Language Models are Contrastive Reasonerscited by 11
  19. 2024Abstraction-of-Thought Makes Language Models Better Reasonerscited by 11
  20. 2023KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrievalcited by 10
  21. 2024Can Github issues be solved with Tree Of Thoughts?cited by 3
  22. 2024Misinforming LLMs: vulnerabilities, challenges and opportunitiescited by 3
  23. 2024Can Separators Improve Chain-of-Thought Prompting?cited by 2

Built on by

Cited by year (2026 to 7 Oct)

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

3 papers.

  1. 2025Accelerating Training Speed of Tiny Recursive Models with Curriculum Guided Adaptive Recursioncited by 5
  2. 2025MARBLE: A Multi-Agent Rule-Based LLM Reasoning Engine for Accident Severity Predictioncited by 0
  3. 2026VERIFY-RL: Verifiable Recursive Decomposition for Reinforcement Learning in Mathematical Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought
  2. 2023Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language Models
  3. 2023Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models
  4. 2025Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts
  5. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning
  6. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  7. 2025SLR: Automated Synthesis for Scalable Logical Reasoning
  8. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models