mlsanityData to 14 Oct 2026

Graph of Thoughts: Solving Elaborate Problems with Large Language Models

arXiv 2308.09687 ↗First posted 18 Aug 2023cs.CL cs.AI cs.LGcited by 886

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

Abstract (arXiv)

We introduce Graph of Thoughts (GoT): a framework that advances prompting capabilities in large language models (LLMs) beyond those offered by paradigms such as Chain-of-Thought or Tree of Thoughts (ToT). The key idea and primary advantage of GoT is the ability to model the information generated by an LLM as an arbitrary graph, where units of information ("LLM thoughts") are vertices, and edges correspond to dependencies between these vertices. This approach enables combining arbitrary LLM thoughts into synergistic outcomes, distilling the essence of whole networks of thoughts, or enhancing thoughts using feedback loops. We illustrate that GoT offers advantages over state of the art on different tasks, for example increasing the quality of sorting by 62% over ToT, while simultaneously reducing costs by >31%. We ensure that GoT is extensible with new thought transformations and thus can be used to spearhead new prompting schemes. This work brings the LLM reasoning closer to human thinking or brain mechanisms such as recurrence, both of which form complex networks.

Key facts. Cited by 886 papers in the map (data through 14 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 56 of its 90 references that are in the map. First posted on arXiv 18 Aug 2023.

Builds on

56 of 90 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models6 May
  2. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data24 Feb
  3. 2022Reasoning with Language Model Prompting: A Survey19 Dec
  4. 2022Complexity-Based Prompting for Multi-Step Reasoning3 Oct
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 50

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  7. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  8. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  9. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  10. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  11. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  12. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
38 more
  1. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  2. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  3. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
  4. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  5. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  6. 2023Teaching Large Language Models to Self-Debugcited by 988
  7. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
  8. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  9. 2017Representation Learning on Graphs: Methods and Applicationscited by 457
  10. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 398
  11. 2018Deep Learning on Graphs: A Surveycited by 393
  12. 2023Language Models can Solve Computer Taskscited by 372
  13. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  14. 2021AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Promptscited by 268
  15. 2023Large Language Model Guided Tree-of-Thoughtcited by 221
  16. 2023REFINER: Reasoning Feedback on Intermediate Representationscited by 205
  17. 2023Self-Evaluation Guided Beam Search for Reasoningcited by 196
  18. 2023Planning with Large Language Models for Code Generationcited by 182
  19. 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 164
  20. 2020Machine Learning on Graphs: A Model and Comprehensive Taxonomycited by 156
  21. 2022PromptChainer: Chaining Large Language Model Prompts through Visual Programmingcited by 134
  22. 2022Language Model Cascadescited by 107
  23. 2021A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Levelcited by 96
  24. 2021Explanation-Based Human Debugging of NLP Models: A Surveycited by 53
  25. 2021Putting Humans in the Natural Language Processing Loop: A Surveycited by 40
  26. 2022Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysiscited by 29
  27. 2019Demystifying Graph Databases: Analysis and Taxonomy of Data Organization, System Designs, and Graph Queriescited by 22
  28. 2021Motif Prediction with Graph Neural Networkscited by 18
  29. 2021SISA: Set-Centric Instruction Set Architecture for Graph Mining on Processing-in-Memory Systemscited by 17
  30. 2022A survey on improving NLP models with human explanationscited by 15
  31. 2019Practice of Streaming Processing of Dynamic Graphs: Concepts, Models, and Systemscited by 12
  32. 2022Neural Graph Databasescited by 11
  33. 2019Communication-Efficient Jaccard Similarity for High-Performance Distributed Genome Comparisonscited by 10
  34. 2021GraphMineSuite: Enabling High-Performance and Programmable Graph Mining Algorithms with Set Algebracited by 10
  35. 2021Learning Combinatorial Node Labeling Algorithmscited by 10
  36. 2022ProbGraph: High-Performance and High-Accuracy Graph Mining with Probabilistic Set Representationscited by 7
  37. 2019Low-Latency Graph Streaming Using Compressed Purely-Functional Treescited by 6
  38. 2015Arabesque: A System for Distributed Graph Mining - Extended versioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 83; 2024: 270; 2025: 299; 2026: 234.

886 papers.

Sort:

By area:

  1. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  2. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 991
  3. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Modelscited by 665
  4. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 574
  5. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 570
  6. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 551
  7. 2023DriveLM: Driving with Graph Visual Question Answeringcited by 536
  8. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 464
  9. 2024Understanding the planning of LLM agents: A surveycited by 421
  10. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 392
  11. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 328
  12. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 320
38 more
  1. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 316
  2. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 309
  3. 2025Chain of Draft: Thinking Faster by Writing Lesscited by 297
  4. 2025O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruningcited by 279
  5. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningcited by 263
  6. 2025Training Language Models to Reason Efficientlycited by 247
  7. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 241
  8. 2024Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Modelscited by 235
  9. 2024Data Interpreter: An LLM Agent For Data Sciencecited by 225
  10. 2024Agent Q: Advanced Reasoning and Learning for Autonomous AI Agentscited by 208
  11. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 205
  12. 2024A Survey on Efficient Inference for Large Language Modelscited by 205
  13. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 205
  14. 2023Large Language Models on Graphs: A Comprehensive Surveycited by 192
  15. 2023Efficient Large Language Models: A Surveycited by 186
  16. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 182
  17. 2023An LLM Compiler for Parallel Function Callingcited by 179
  18. 2023Implicit Chain of Thought Reasoning via Knowledge Distillationcited by 176
  19. 2024Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Searchcited by 175
  20. 2023Compositional Chain-of-Thought Prompting for Large Multimodal Modelscited by 164
  21. 2025Dynamic Cheatsheet: Test-Time Learning with Adaptive Memorycited by 163
  22. 2024Teaching Large Language Models to Reason with Reinforcement Learningcited by 160
  23. 2024The pitfalls of next-token predictioncited by 160
  24. 2024Distilling System 2 into System 1cited by 159
  25. 2024GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generationcited by 153
  26. 2024Tree Search for Language Model Agentscited by 151
  27. 2023Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generationcited by 148
  28. 2025Scaling Long-Horizon LLM Agent via Context-Foldingcited by 148
  29. 2024Evaluation of Retrieval-Augmented Generation: A Surveycited by 146
  30. 2024Stream of Search (SoS): Learning to Search in Languagecited by 145
  31. 2025SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvementcited by 145
  32. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 143
  33. 2024From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Modelscited by 137
  34. 2025EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecyclecited by 137
  35. 2024Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planningcited by 135
  36. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 135
  37. 2025Where LLM Agents Fail and How They can Learn From Failurescited by 133
  38. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospectscited by 132

50 most cited of 886 All 886 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models
  2. 2023Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought
  3. 2024Self-guided Knowledgeable Network of Thoughts: Amplifying Reasoning with Large Language Models
  4. 2024Chain-of-Thought in Large Language Models: Decoding, Projection, and Activation
  5. 2023MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models
  6. 2025On the Thinking-Language Modeling Gap in Large Language Models
  7. 2025Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM
  8. 2026CoEvoT: Co-Evolving Chain-of-Thought Prompting for Graph-LLM Reasoning