mlsanityData to 14 Oct 2026

Blind Spot Navigation in Large Language Model Reasoning with Thought Space Explorer

arXiv 2410.24155 ↗First posted 31 Oct 2024cs.CLcited by 7

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Large language models have shown strong reasoning capabilities through chain-structured methods such as Chain-of-Thought. Recent studies optimize thought structures by generating parallel or tree-like structures, switching between long and short reasoning modes, or aligning reasoning steps with task performance. However, these approaches mainly rely on previously generated logical directions of the chains, which ignore the unexplored regions of the solution space. Such a phenomenon is defined as blind spots, which limit the diversity and effectiveness of the reasoning process. To this end, we propose the ``Thought Space Explorer'' (TSE), a framework for navigating and expanding thought structures to overcome blind spots in LLM reasoning. Our TSE first identifies key nodes with high impact, then generates new nodes by integrating information from multiple chains. Finally, it extends new branches through connection strategies. We conduct a series of experiments on math and QA benchmarks. Compared with existing baseline methods, TSE improves the accuracy of both the final answer and intermediate reasoning steps, while maintaining a better effectiveness-efficiency trade-off for practical deployment.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 29 of its 54 references that are in the map. First posted on arXiv 31 Oct 2024.

Builds on

29 of 54 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024On the Diagram of Thought16 Sep
  2. 2024RATT: A Thought Structure for Coherent and Correct LLM Reasoning4 Jun
  3. 2022Towards Reasoning in Large Language Models: A Survey20 Dec

Other references · 26

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  4. 2024GPT-4o System Cardcited by 4,588
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  6. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  7. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Trainingcited by 295
  8. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningcited by 263
  9. 2024Chain of Thought Empowers Transformers to Solve Inherently Serial Problemscited by 260
  10. 2023Large Language Model Guided Tree-of-Thoughtcited by 221
  11. 2024Chain-of-Thought Reasoning Without Promptingcited by 210
  12. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
14 more
  1. 2022Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanationscited by 159
  2. 2024Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worsecited by 109
  3. 2024Chain of Thoughtlessness? An Analysis of CoT in Planningcited by 103
  4. 2024Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMscited by 96
  5. 2022Solving Math Word Problems via Cooperative Reasoning induced Language Modelscited by 77
  6. 2023Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Searchcited by 75
  7. 2023WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipediacited by 67
  8. 2024Interpretable Contrastive Monte Carlo Tree Search Reasoningcited by 64
  9. 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 50
  10. 2024Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMscited by 48
  11. 2024Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Modelscited by 23
  12. 2024Prototypical Reward Network for Data-Efficient RLHFcited by 22
  13. 2024TimeToM: Temporal Space is the Key to Unlocking the Door of Large Language Models' Theory-of-Mindcited by 21
  14. 2024Self-Harmonized Chain of Thoughtcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 3.

7 papers.

  1. 2024LoRA-LiteE: A Computationally Efficient Framework for Chatbot Preference-Tuningcited by 10
  2. 2025DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Modelscited by 6
  3. 2026StaRPO: Stability-Augmented Reinforcement Policy Optimizationcited by 5
  4. 2025ThoughtProbe: Classifier-Guided Thought Space Exploration Leveraging LLM Intrinsic Reasoningcited by 4
  5. 2025SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Modelscited by 2
  6. 2026Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learningcited by 1
  7. 2026BrailleBench: Investigating Multi-Criteria Braille Comprehension in Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance
  2. 2025ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations
  3. 2025Chain or tree? Re-evaluating complex reasoning from the perspective of a matrix of thought
  4. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  5. 2026Beyond Fixed Budgets: Characterizing the Inelasticity and Limitations of Tree-of-Thought Reasoning Strategies
  6. 2023Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
  7. 2025Beyond Chains of Thought: Benchmarking Latent-Space Reasoning Abilities in Large Language Models
  8. 2025Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning