mlsanityData to 7 Oct 2026

Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought

arXiv 2308.08614 ↗First posted 16 Aug 2023cs.LG cs.AI cs.CLcited by 41

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

Recent advancements in large-scale models, such as GPT-4, have showcased remarkable capabilities in addressing standard queries. However, when facing complex problems that require multi-step logical reasoning, their accuracy dramatically decreases. Current research has explored the realm of textitprompting engineering to bolster the inferential capacities of these models. Our paper unveils a pioneering prompting technique, dubbed textitGraph of Thoughts (GoT). Through testing on a trio of escalating challenges: the 24-point game, resolution of high-degree polynomial equations, and derivation of formulas for recursive sequences, our method outperformed GPT-4, achieving accuracy improvements of 89.7%, 86%, and 56% for each respective task. Moreover, when juxtaposed with the state-of-the-art (SOTA) prompting method, textitTree of Thought (ToT), our approach registered an average accuracy boost of 23%, 24%, and 15%.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 17 of its 27 references that are in the map. First posted on arXiv 16 Aug 2023.

Builds on

17 of 27 references.

Closest ancestors · 5

Same direction, newest first

  1. 2022Distilling Reasoning Capabilities into Smaller Language Models1 Dec
  2. 2022Automatic Chain of Thought Prompting in Large Language Models7 Oct
  3. 2022Large Language Models are Zero-Shot Reasoners24 May
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 12

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  4. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  5. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  6. 2019Analysing Mathematical Reasoning Abilities of Neural Modelscited by 331
  7. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  8. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  9. 2023ART: Automatic multi-step reasoning and tool-use for large language modelscited by 193
  10. 2022PromptChainer: Chaining Large Language Model Prompts through Visual Programmingcited by 134
  11. 2022Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Modelscited by 70
  12. 2023Prompting Large Language Models With the Socratic Methodcited by 43

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 9; 2024: 21; 2025: 9; 2026: 2.

41 papers.

Sort:

By area:

  1. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  2. 2025Chain of Draft: Thinking Faster by Writing Lesscited by 290
  3. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 217
  4. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  5. 2023Compositional Chain-of-Thought Prompting for Large Multimodal Modelscited by 160
  6. 2023Branch-Solve-Merge Improves Large Language Model Evaluation and Generationcited by 104
  7. 2024Large Language Models Meet NLP: A Surveycited by 102
  8. 2023Learning From Mistakes Makes LLM Better Reasonercited by 97
  9. 2024Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoningcited by 69
  10. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  11. 2024Visual Agents as Fast and Slow Thinkerscited by 53
  12. 2025Logical Reasoning in Large Language Models: A Surveycited by 52
29 more
  1. 2024Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learningcited by 49
  2. 2024DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLMcited by 45
  3. 2024Puzzle Solving using Reasoning of Large Language Models: A Surveycited by 44
  4. 2024MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problemscited by 41
  5. 2023DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacycited by 34
  6. 2024Cantor: Inspiring Multimodal Chain-of-Thought of MLLMcited by 34
  7. 2025Pruning the Unsurprising: Efficient LLM Reasoning via First-Token Surprisalcited by 32
  8. 2024GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Groundingcited by 26
  9. 2023Mathematical Language Models: A Surveycited by 24
  10. 2024TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMscited by 21
  11. 2023Graph Meets LLMs: Towards Large Graph Modelscited by 19
  12. 2023Integrating Graphs with Large Language Models: Methods and Prospectscited by 18
  13. 2024UniCoder: Scaling Code Large Language Model via Universal Codecited by 18
  14. 2024Optimizing Language Model's Reasoning Abilities with Weak Supervisioncited by 15
  15. 2024Distilling Reasoning Ability from Large Language Models with Adaptive Thinkingcited by 13
  16. 2024Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Modelscited by 9
  17. 2025Fast-Slow-Thinking: Complex Task Solving with Large Language Modelscited by 7
  18. 2023Enhancing Logical Reasoning in Large Language Models to Facilitate Legal Applicationscited by 6
  19. 2025Is Depth All You Need? An Exploration of Iterative Reasoning in LLMscited by 6
  20. 2024Logicbreaks: A Framework for Understanding Subversion of Rule-based Inferencecited by 3
  21. 2024Exploring the Role of Reasoning Structures for Constructing Proofs in Multi-Step Natural Language Reasoning with Large Language Modelscited by 3
  22. 2024Poor-Supervised Evaluation for SuperLLM via Mutual Consistencycited by 1
  23. 2024Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyondcited by 1
  24. 2025From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Modelscited by 1
  25. 2024Seeing the Undefined: Chain-of-Action for Generative Semantic Labelscited by 0
  26. 2025MARCO: Meta-Reflection with Cross-Referencing for Code Reasoningcited by 0
  27. 2025Efficiency Will Not Lead to Sustainable Reasoning AIcited by 0
  28. 2026From Perception to Action: Spatial AI Agents and World Modelscited by 0
  29. 2026Topology of Reasoning: Retrieved Cell Complex-Augmented Generation for Textual Graph Question Answeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models
  2. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Models
  3. 2024Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Models
  4. 2025Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures
  5. 2023Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models
  6. 2024Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns
  7. 2024Judgment-of-Thought Prompting: A Courtroom-Inspired Framework for Binary Logical Reasoning with Large Language Models
  8. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Models