mlsanityData to 14 Oct 2026

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review

arXiv 2508.12265 ↗First posted 17 Aug 2025cs.CLcited by 2

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable progress in reasoning across diverse domains. However, effective reasoning in real-world tasks requires adapting the reasoning strategy to the demands of the problem, ranging from fast, intuitive responses to deliberate, step-by-step reasoning and tool-augmented thinking. Drawing inspiration from cognitive psychology, we propose a novel taxonomy of LLM reasoning strategies along two knowledge boundaries: a fast/slow boundary separating intuitive from deliberative processes, and an internal/external boundary distinguishing reasoning grounded in the model's parameters from reasoning augmented by external tools. We systematically survey recent work on adaptive reasoning in LLMs and categorize methods based on key decision factors. We conclude by highlighting open challenges and future directions toward more adaptive, efficient, and reliable LLMs.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 47 of its 70 references that are in the map. First posted on arXiv 17 Aug 2025.

Builds on

47 of 70 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Thinking with Nothinking Calibration: A New In-Context Learning Paradigm in Reasoning Large Language Models5 Aug
  2. 2025EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes15 Jul
  3. 2025Qwen3 Technical Report14 May

Other references · 44

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  4. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  5. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  6. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 719
  7. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 431
  8. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMscited by 392
  9. 2022Confident Adaptive Language Modelingcited by 310
  10. 2025Dynamic Early Exit in Reasoning Modelscited by 219
  11. 2025Reasoning Models Know When They're Right: Probing Hidden States for Self-Verificationcited by 159
  12. 2025Llama-Nemotron: Efficient Reasoning Modelscited by 158
32 more
  1. 2025AdaptThink: Reasoning Models Can Learn When to Thinkcited by 147
  2. 2025Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learningcited by 110
  3. 2025AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learningcited by 87
  4. 2025Think Only When You Need with Large Hybrid-Reasoning Modelscited by 66
  5. 2024DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Modelscited by 63
  6. 2025Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RLcited by 62
  7. 2024SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generationcited by 40
  8. 2024Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verificationcited by 40
  9. 2025ThinkSwitcher: When to Think Hard, When to Think Fastcited by 37
  10. 2025Z1: Efficient Test-time Scaling with Codecited by 35
  11. 2025Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspectivecited by 34
  12. 2025Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Homecited by 33
  13. 2025Uncertainty-Guided Chain-of-Thought for Code Generation with LLMscited by 32
  14. 2025Adaptive Tool Use in Large Language Models with Meta-Cognition Triggercited by 30
  15. 2024Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMscited by 27
  16. 2025Let LRMs Break Free from Overthinking via Self-Braking Tuningcited by 27
  17. 2024To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contextscited by 25
  18. 2025To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximizationcited by 25
  19. 2024Adaptive Retrieval-Augmented Generation for Conversational Systemscited by 22
  20. 2024DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Modelscited by 20
  21. 2025R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learningcited by 20
  22. 2025Alignment for Efficient Tool Calling of Large Language Modelscited by 17
  23. 2025MUR: Momentum Uncertainty guided Reasoning for Large Language Modelscited by 17
  24. 2025TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compressioncited by 16
  25. 2025Position: The Real Barrier to LLM Agent Usability is Agentic ROIcited by 12
  26. 2025AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Modelscited by 12
  27. 2025KAT-V1: Kwai-AutoThink Technical Reportcited by 12
  28. 2025Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoningcited by 8
  29. 2023The Web Can Be Your Oyster for Improving Large Language Modelscited by 7
  30. 2024Adapting While Learning: Grounding LLMs for Scientific Problems with Intelligent Tool Usage Adaptationcited by 7
  31. 2025SynapseRoute: An Auto-Route Switching Framework on Dual-State Large Language Modelcited by 7
  32. 2024Toolken+: Improving LLM Tool Usage with Reranking and a Reject Optioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026M3-ACE: Rectifying Visual Perception in Multimodal Math Reasoning via Multi-Agentic Context Engineeringcited by 1
  2. 2026Mitigating Context Interference for Reliable and Efficient Search Agentscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes
  2. 2022Towards Reasoning in Large Language Models: A Survey
  3. 2025Thinking Isn't an Illusion: Overcoming the Limitations of Reasoning Models via Tool Augmentations
  4. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  5. 2024Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey
  6. 2025Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinking
  7. 2025Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
  8. 2024LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models