mlsanityData to 14 Oct 2026

Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective

arXiv 2511.14772 ↗First posted 1 Nov 2025cs.CL cs.AIcited by 2

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

Abstract (arXiv)

With this paper, we survey techniques for improving the predictive accuracy of pretrained large language models by allocating additional compute at inference time. In categorizing test-time scaling methods, we place special emphasis on how a problem is decomposed into subproblems and on the topological organization of these subproblems whether sequential, parallel, or tree-structured. This perspective allows us to unify diverse approaches such as Chain-of-Thought, Branch-Solve-Merge, and Tree-of-Thought under a common lens. We further synthesize existing analyses of these techniques, highlighting their respective strengths and weaknesses, and conclude by outlining promising directions for future research

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 33 of its 91 references that are in the map. First posted on arXiv 1 Nov 2025.

Builds on

33 of 91 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025A*-Decoding: Token-Efficient Inference Scaling19 May
  2. 2025Demystifying Long Chain-of-Thought Reasoning in LLMs5 Feb
  3. 2024Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models1 Aug

Other references · 30

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  3. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  4. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 991
  5. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 574
  6. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 517
  7. 2023Active Retrieval Augmented Generationcited by 516
  8. 2025Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRscited by 377
  9. 2024Justice or Prejudice? Quantifying Biases in LLM-as-a-Judgecited by 368
  10. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  11. 2021An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQAcited by 301
  12. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningcited by 263
18 more
  1. 2024Self-Preference Bias in LLM-as-a-Judgecited by 258
  2. 2025Imagine while Reasoning in Space: Multimodal Visualization-of-Thoughtcited by 206
  3. 2025When More is Less: Understanding Chain-of-Thought Length in LLMscited by 183
  4. 2019On the Measure of Intelligencecited by 144
  5. 2023Chip-Chat: Challenges and Opportunities in Conversational Hardware Designcited by 140
  6. 2023Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselvescited by 123
  7. 2024ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Explorationcited by 103
  8. 2023AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learncited by 97
  9. 2023System 2 Attention (is something you might need too)cited by 89
  10. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Draftingcited by 77
  11. 2024Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Modelscited by 43
  12. 2023Zero-Shot Video Question Answering with Procedural Programscited by 37
  13. 2025VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Searchcited by 36
  14. 2025Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAGcited by 23
  15. 2024Enhancing LLM Reasoning with Multi-Path Collaborative Reactive and Reflection agentscited by 15
  16. 2025I-MCTS: Enhancing Agentic AutoML via Introspective Monte Carlo Tree Searchcited by 14
  17. 2024MC-NEST: Enhancing Mathematical Reasoning in Large Language Models leveraging a Monte Carlo Self-Refine Treecited by 7
  18. 2024Mixture of Rationale: Multi-Modal Reasoning Mixture for Visual Question Answeringcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculuscited by 3
  2. 2026Can Decision Trees Teach Large Language Models? Distilling Verbalized Knowledge for Molecular Property Predictioncited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025The Art of Scaling Test-Time Compute for Large Language Models
  2. 2025A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?
  3. 2025Faster and Better LLMs via Latency-Aware Test-Time Scaling
  4. 2025Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
  5. 2025Are We Scaling the Right Thing? A System Perspective on Test-Time Scaling
  6. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
  7. 2025Scaling Test-time Compute for LLM Agents
  8. 2025The Energy Cost of Reasoning: Analyzing Energy Usage in LLMs with Test-time Compute