mlsanityData to 14 Oct 2026

Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation

arXiv 2311.04254 ↗First posted 7 Nov 2023cs.AI cs.LGcited by 74

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

Abstract (arXiv)

Recent advancements in Large Language Models (LLMs) have revolutionized decision-making by breaking down complex problems into more manageable language sequences referred to as "thoughts". An effective thought design should consider three key perspectives: performance, efficiency, and flexibility. However, existing thought can at most exhibit two of these attributes. To address these limitations, we introduce a novel thought prompting approach called "Everything of Thoughts" (XoT) to defy the law of "Penrose triangle of existing thought paradigms. XoT leverages pretrained reinforcement learning and Monte Carlo Tree Search (MCTS) to incorporate external domain knowledge into thoughts, thereby enhancing LLMs' capabilities and enabling them to generalize to unseen problems efficiently. Through the utilization of the MCTS-LLM collaborative thought revision framework, this approach autonomously produces high-quality comprehensive cognitive mappings with minimal LLM interactions. Additionally, XoT empowers LLMs to engage in unconstrained thinking, allowing for flexible cognitive mappings for problems with multiple solutions. We evaluate XoT on several challenging multi-solution problem-solving tasks, including Game of 24, 8-Puzzle, and Pocket Cube. Our results demonstrate that XoT significantly outperforms existing approaches. Notably, XoT can yield multiple solutions with just one LLM call, showcasing its remarkable proficiency in addressing complex problems across diverse domains.

Key facts. Cited by 74 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 26 of its 44 references that are in the map. First posted on arXiv 7 Nov 2023.

Builds on

26 of 44 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Models18 Aug
  2. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting7 May
  3. 2022Automatic Chain of Thought Prompting in Large Language Models7 Oct

Other references · 23

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  4. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  5. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  6. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 752
  7. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 398
  8. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 353
  9. 2017Deep Reinforcement Learning: An Overviewcited by 333
  10. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 333
  11. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Trainingcited by 295
  12. 2023Mathematical Capabilities of ChatGPTcited by 268
11 more
  1. 2023Large Language Model Guided Tree-of-Thoughtcited by 221
  2. 2023Grounding Large Language Models in Interactive Environments with Online Reinforcement Learningcited by 195
  3. 2023Translating Natural Language to Planning Goals with Large-Language Modelscited by 133
  4. 2023Can Large Language Models Really Improve by Self-critiquing Their Own Plans?cited by 108
  5. 2023Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generationcited by 105
  6. 2023GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problemscited by 89
  7. 2023Automatic Root Cause Analysis via Large Language Models for Cloud Incidentscited by 84
  8. 2023Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decodingcited by 60
  9. 2023ChatGPT versus Traditional Question Answering for Knowledge Graphs: Current Status and Future Directions Towards Knowledge Graph Chatbotscited by 47
  10. 2023Skill Reinforcement Learning and Planning for Open-World Long-Horizon Taskscited by 36
  11. 2017Solving the Rubik's Cube Optimally is NP-completecited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 36; 2025: 25; 2026: 9.

74 papers.

Sort:

By area:

  1. 2023DriveLM: Driving with Graph Visual Question Answeringcited by 536
  2. 2023Efficient Large Language Models: A Surveycited by 186
  3. 2024Large Language Model-Brained GUI Agents: A Surveycited by 162
  4. 2024UFO: A UI-Focused Agent for Windows OS Interactioncited by 148
  5. 2024Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solverscited by 138
  6. 2024Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizingcited by 125
  7. 2024Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoningcited by 110
  8. 2024Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMscited by 96
  9. 2025Efficient Reasoning Models: A Surveycited by 95
  10. 2024LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoningcited by 91
  11. 2024Self-playing Adversarial Language Game Enhances LLM Reasoningcited by 83
  12. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
38 more
  1. 2025A Survey on (M)LLM-Based GUI Agentscited by 62
  2. 2025Atom of Thoughts for Markov LLM Test-Time Scalingcited by 54
  3. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  4. 2024Puzzle Solving using Reasoning of Large Language Models: A Surveycited by 45
  5. 2025Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Modelscited by 44
  6. 2024RATT: A Thought Structure for Coherent and Correct LLM Reasoningcited by 41
  7. 2025UFO2: The Desktop AgentOScited by 41
  8. 2024Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraintcited by 39
  9. 2024Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpuscited by 32
  10. 2025Reward Is Enough: LLMs Are In-Context Reinforcement Learnerscited by 31
  11. 2024Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examplescited by 30
  12. 2025Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insightscited by 30
  13. 2024Large Language Models can Deliver Accurate and Interpretable Time Series Anomaly Detectioncited by 29
  14. 2023Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruningcited by 26
  15. 2024RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Modelscited by 25
  16. 2024TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decisioncited by 23
  17. 2023Xpert: Empowering Incident Management with Query Recommendations via Large Language Modelscited by 22
  18. 2024Can LLMs Solve longer Math Word Problems Better?cited by 22
  19. 2025Monte Carlo Planning with Large Language Model for Text-Based Game Agentscited by 22
  20. 2024LLM-Generated Black-box Explanations Can Be Adversarially Helpfulcited by 21
  21. 2024Large Action Models: From Inception to Implementationcited by 18
  22. 2025Text2Grad: Reinforcement Learning from Natural Language Feedbackcited by 18
  23. 2024Autonomous Agents for Collaborative Task under Information Asymmetrycited by 16
  24. 2024Can We Verify Step by Step for Incorrect Answer Detection?cited by 15
  25. 2025TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generationcited by 15
  26. 2024What Are Step-Level Reward Models Rewarding? Counterintuitive Findings from MCTS-Boosted Mathematical Reasoningcited by 14
  27. 2025Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoningcited by 11
  28. 2025Multi-LLM Collaborative Search for Complex Problem Solvingcited by 10
  29. 2024Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Modelscited by 9
  30. 2024MMAC-Copilot: Multi-modal Agent Collaboration Operating Copilotcited by 8
  31. 2025Toward Structured Knowledge Reasoning: Contrastive Retrieval-Augmented Generation on Experiencecited by 8
  32. 2026Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Modelscited by 8
  33. 2024On the Empirical Complexity of Reasoning and Planning in LLMscited by 6
  34. 2025Complex LLM Planning via Automated Heuristics Discoverycited by 6
  35. 2024RuAG: Learned-rule-augmented Generation for Large Language Modelscited by 5
  36. 2025PuzzlePlex: Benchmarking Foundation Models on Reasoning and Planning with Puzzlescited by 5
  37. 2026TreeAdv: Tree-Structured Advantage Redistribution for Group-Based RLcited by 5
  38. 2024A Study on Training and Developing Large Language Models for Behavior Tree Generationcited by 4

50 most cited of 74 All 74 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning
  2. 2026Thoughts-as-Planning: Latent World Models for Chain-of-Thoughts Optimization via Reinforcement Planning
  3. 2023Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models
  4. 2024MTMT: Consolidating Multiple Thinking Modes to Form a Thought Tree for Strengthening LLM
  5. 2025Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
  6. 2025Universe of Thoughts: Enabling Creative Reasoning with Large Language Models
  7. 2023Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking
  8. 2023Unleashing the Creative Mind: Language Model As Hierarchical Policy For Improved Exploration on Challenging Problem Solving