A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning

Yixin Ji, Juntao Li, Yang Xiang, Hai Ye, Kaixin Wu, Kai Yao, Jia Xu, Linjian Mo, Min Zhang

TL;DR

This paper provides the first systematic survey of test-time compute, exploring how scaling computational effort during inference allows models to transition from "fast" intuitive responses (System-1) to "slow" deliberate reasoning (System-2). It categorizes methods ranging from early test-time adaptation for robustness to modern search and self-correction strategies that power state-of-the-art reasoning models like OpenAI’s o1 and DeepSeek-R1.

What Problem Does This Paper Address?

Traditional deep learning has relied heavily on scaling training-time compute (more data, larger models). However, we are hitting diminishing returns due to data scarcity and the inherent limitations of "System-1" thinking—where models provide immediate, pattern-based responses that lack robustness and struggle with complex, multi-step logic.

The authors address the growing need to understand how we can instead scale test-time compute. The goal is to enable "System-2" thinking: a deliberate, iterative process where a model can brainstorm, verify its own steps, and backtrack when it hits a dead end. This survey organizes the fragmented landscape of inference-time techniques into a coherent taxonomy, tracing the evolution from simple model adaptation to complex tree-based reasoning.

Fig. 1. Illustration of test-time compute in the System-1 and System-2 model.

Methods

The paper organizes test-time compute into two primary categories, further detailed in a comprehensive taxonomy (see Figure 2):

  1. Test-time Adaptation (TTA) for System-1: These methods focus on improving robustness to distribution shifts without necessarily adding complex reasoning.
  2. Parameter Updating: Finetuning a small subset of weights (like normalization layers) on the test sample itself.
  3. Input Modification: Selecting or creating better in-context learning (ICL) demonstrations.
  4. Representation Editing: Using "steering vectors" to modify intermediate activations to reduce toxicity or hallucinations.
  5. Output Calibration: Using external datastores (like $k$NN-MT) to adjust the model's final probability distribution.
  6. Test-time Reasoning (TTR) for System-2: These methods aim to solve complex problems through explicit search and feedback loops.
  7. Feedback Modeling: Developing "Verifiers" (Outcome-based or Process-based Reward Models) or "Critics" (LLMs that provide natural language feedback).
  8. Search Strategies: * Repeated Sampling: Generating multiple paths and using majority voting or Best-of-N selection.
  9. Self-correction: An iterative process where the model critiques and refines its own answer.
  10. Tree Search: Using algorithms like Monte Carlo Tree Search (MCTS) to explore a vast space of reasoning steps, allowing for global optimization and backtracking.
Fig. 2. Taxonomy of test-time computing methods and future directions.

Datasets

The survey reviews a wide array of benchmarks used to evaluate these techniques:

  • Robustness/TTA: ImageNet-C/R/Sketch for vision; MLQA and XQuAD for cross-lingual NLP.
  • Feedback Modeling: RewardBench (evaluating reward model accuracy) and CriticBench (evaluating self-correction capabilities).
  • Reasoning: Classic benchmarks like GSM8K and MATH (now largely "solved" by o1-class models), and newer, harder challenges like FrontierMath and Omni-MATH.
  • Code: HumanEval, MBPP, and the more complex BigCodeBench.

Key Insights and Ideas

  • The Inference Scaling Effect: Just as training compute has scaling laws, inference compute shows a "scaling effect"—the more time/compute a model spends searching and verifying, the better its performance, particularly on difficult tasks.
  • PRMs > ORMs: Process-based Reward Models (PRMs), which grade every individual step of a reasoning chain, are significantly more effective for guiding search than Outcome-based Reward Models (ORMs), which only look at the final answer.
  • The Self-Correction Paradox: While promising, self-correction is not a "silver bullet." The authors note that models often struggle to locate their own errors even if they have the capability to fix them once identified.
  • System-1 to System-2 Transition: TTA can be viewed as "implicit" slow thinking, while TTR (like Chain-of-Thought) is "explicit" slow thinking. The paper argues that combining these—using TTA to adapt the model's underlying knowledge before starting a complex search—is a potent future direction.
Comparison of different search strategies: Repeated sampling, Self-correction, and Tree search.

Key Results

  • Self-Consistency: Simply using majority voting over multiple sampled Chain-of-Thought (CoT) paths can improve accuracy by up to 18% on math reasoning tasks.
  • State of the Art: The survey highlights that while models like o1 have surpassed 90% on MATH, the new FrontierMath benchmark remains a massive challenge, with even the most advanced models scoring below 30%.
  • Efficiency Gains: Techniques like "Token-Budget-Aware" reasoning and "Early Exit" strategies are shown to mitigate the high cost of test-time compute by only "thinking hard" when a problem is actually difficult.

Limitations and Future Work

  • Universal Scaling Laws: Unlike training, there is currently no universal law that predicts performance based on inference compute across different search strategies.
  • Generalization: Most current reasoning models are specialized in math and code; generalizing System-2 thinking to creative writing or general-purpose "agentic" tasks remains difficult.
  • Latent Reasoning: A promising new frontier is "Latent CoT," where models perform reasoning steps in a continuous hidden vector space rather than generating human-readable text, potentially offering massive efficiency gains.
  • Multi-modal Scaling: Extending these search and verification strategies to video and audio modalities is still in its infancy.

Summary updated

Abstract

The remarkable performance of the o1 model in complex reasoning demonstrates that test-time compute scaling can further unlock the model's potential, enabling powerful System-2 thinking. However, there is still a lack of comprehensive surveys for test-time compute scaling. We trace the concept of test-time compute back to System-1 models. In System-1 models, test-time compute addresses distribution shifts and improves robustness and generalization through parameter updating, input modification, representation editing, and output calibration. In System-2 models, it enhances the model's reasoning ability to solve complex problems through repeated sampling, self-correction, and tree search. We organize this survey according to the trend of System-1 to System-2 thinking, highlighting the key role of test-time compute in the transition from System-1 models to weak System-2 models, and then to strong System-2 models. We also point out advanced topics and future directions.
BibTeX
@misc{ji2025survey,
  author = {Yixin Ji and Juntao Li and Yang Xiang and Hai Ye and Kaixin Wu and Kai Yao and Jia Xu and Linjian Mo and Min Zhang},
  title = {{A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning}},
  year = {2025},
  eprint = {2501.02497},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.02497},
}
Figure