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

arXiv: https://arxiv.org/abs/2508.12265 · HTML: https://mlsanity.com/paper/2508.12265/

## 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.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 47)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025)
- [Confident Adaptive Language Modeling](https://mlsanity.com/paper/2207.07061/) (2022)
- [Dynamic Early Exit in Reasoning Models](https://mlsanity.com/paper/2504.15895/) (2025)
- [Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification](https://mlsanity.com/paper/2504.05419/) (2025)
- [Llama-Nemotron: Efficient Reasoning Models](https://mlsanity.com/paper/2505.00949/) (2025)
- [AdaptThink: Reasoning Models Can Learn When to Think](https://mlsanity.com/paper/2505.13417/) (2025)
- [Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning](https://mlsanity.com/paper/2505.01441/) (2025)
- [AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning](https://mlsanity.com/paper/2505.11896/) (2025)
- [Think Only When You Need with Large Hybrid-Reasoning Models](https://mlsanity.com/paper/2505.14631/) (2025)
- [DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models](https://mlsanity.com/paper/2403.10081/) (2024)
- [Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL](https://mlsanity.com/paper/2505.10832/) (2025)
- [SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation](https://mlsanity.com/paper/2406.19215/) (2024)
- [Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification](https://mlsanity.com/paper/2410.05318/) (2024)
- [ThinkSwitcher: When to Think Hard, When to Think Fast](https://mlsanity.com/paper/2505.14183/) (2025)
- [Z1: Efficient Test-time Scaling with Code](https://mlsanity.com/paper/2504.00810/) (2025)
- [Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective](https://mlsanity.com/paper/2505.12886/) (2025)
- [Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home](https://mlsanity.com/paper/2501.12835/) (2025)
- [Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs](https://mlsanity.com/paper/2503.15341/) (2025)
- [EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes](https://mlsanity.com/paper/2507.11407/) (2025)
- [Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger](https://mlsanity.com/paper/2502.12961/) (2025)
- [Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs](https://mlsanity.com/paper/2402.10612/) (2024)
- [Let LRMs Break Free from Overthinking via Self-Braking Tuning](https://mlsanity.com/paper/2505.14604/) (2025)

## Built on by (most cited first, 2 of 2)

- [M3-ACE: Rectifying Visual Perception in Multimodal Math Reasoning via Multi-Agentic Context Engineering](https://mlsanity.com/paper/2603.08369/) (2026)
- [Mitigating Context Interference for Reliable and Efficient Search Agents](https://mlsanity.com/paper/2608.10743/) (2026)

## 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.