# Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory

arXiv: https://arxiv.org/abs/2505.10981 · HTML: https://mlsanity.com/paper/2505.10981/

## Key facts

- Cited by 10 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 17 of its 70 references that are in the map.
- First posted on arXiv 16 May 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 17 of 17)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B](https://mlsanity.com/paper/2406.07394/) (2024)
- [Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning](https://mlsanity.com/paper/2502.18080/) (2025)
- [Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning](https://mlsanity.com/paper/2412.09078/) (2024)
- [Demystifying Chains, Trees, and Graphs of Thoughts](https://mlsanity.com/paper/2401.14295/) (2024)
- [A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning](https://mlsanity.com/paper/2501.02497/) (2025)
- [Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization](https://mlsanity.com/paper/2501.17974/) (2025)
- [Provable Scaling Laws for the Test-Time Compute of Large Language Models](https://mlsanity.com/paper/2411.19477/) (2024)
- [Scaling LLM Inference with Optimized Sample Compute Allocation](https://mlsanity.com/paper/2410.22480/) (2024)

## Built on by (most cited first, 10 of 10)

- [Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models](https://mlsanity.com/paper/2508.09138/) (2025)
- [Test-Time Reinforcement Learning for GUI Grounding via Region Consistency](https://mlsanity.com/paper/2508.05615/) (2025)
- [Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning](https://mlsanity.com/paper/2511.01016/) (2025)
- [Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning](https://mlsanity.com/paper/2511.01191/) (2025)
- [Inference-Time Scaling for Joint Audio-Video Generation](https://mlsanity.com/paper/2606.03183/) (2026)
- [AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis](https://mlsanity.com/paper/2604.05900/) (2026)
- [Decoding Ambiguous Emotions with Test-Time Scaling in Audio-Language Models](https://mlsanity.com/paper/2602.03873/) (2026)
- [Interpretable Adaptive Sampling for LLM Test-Time Scaling](https://mlsanity.com/paper/2608.03961/) (2026)
- [A Hybrid Method for Low-Resource Named Entity Recognition](https://mlsanity.com/paper/2605.04489/) (2026)
- [VlogReward: Learning Multi-Dimensional Evaluation for Vlog Editing](https://mlsanity.com/paper/2607.22632/) (2026)

## Abstract (arXiv)

Recently, scaling test-time compute on Large Language Models (LLM) has garnered wide attention. However, there has been limited investigation of how various reasoning prompting strategies perform as scaling. In this paper, we focus on a standard and realistic scaling setting: majority voting. We systematically conduct experiments on 6 LLMs × 8 prompting strategies × 6 benchmarks. Experiment results consistently show that as the sampling time and computational overhead increase, complicated prompting strategies with superior initial performance gradually fall behind simple Chain-of-Thought. We analyze this phenomenon and provide theoretical proofs. Additionally, we propose a probabilistic method to efficiently predict scaling performance and identify the best prompting strategy under large sampling times, eliminating the need for resource-intensive inference processes in practical applications. Furthermore, we introduce two ways derived from our theoretical analysis to significantly improve the scaling performance. We hope that our research can promote to re-examine the role of complicated prompting, unleash the potential of simple prompting strategies, and provide new insights for enhancing test-time scaling performance. Code is available at https://github.com/MraDonkey/rethinkingprompting.