# Mitigating Strategy-Selection Bias in Reasoning for More Effective Test-Time Scaling

arXiv: https://arxiv.org/abs/2509.17905 · HTML: https://mlsanity.com/paper/2509.17905/

## Key facts

- Cited by 3 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 18 of its 28 references that are in the map.
- First posted on arXiv 22 Sep 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, 18 of 18)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?](https://mlsanity.com/paper/2503.24235/) (2025)
- [Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2503.12605/) (2025)
- [M3CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought](https://mlsanity.com/paper/2405.16473/) (2024)
- [Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data](https://mlsanity.com/paper/2302.12822/) (2023)
- [Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?](https://mlsanity.com/paper/2502.12215/) (2025)
- [Contrastive Chain-of-Thought Prompting](https://mlsanity.com/paper/2311.09277/) (2023)
- [A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning](https://mlsanity.com/paper/2501.02497/) (2025)
- [Generative AI Act II: Test Time Scaling Drives Cognition Engineering](https://mlsanity.com/paper/2504.13828/) (2025)
- [MetaScale: Test-Time Scaling with Evolving Meta-Thoughts](https://mlsanity.com/paper/2503.13447/) (2025)
- [Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models](https://mlsanity.com/paper/2505.20522/) (2025)
- [Is Depth All You Need? An Exploration of Iterative Reasoning in LLMs](https://mlsanity.com/paper/2502.10858/) (2025)

## Built on by (most cited first, 3 of 3)

- [Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking](https://mlsanity.com/paper/2509.23392/) (2025)
- [Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs](https://mlsanity.com/paper/2510.04140/) (2025)
- [When Does Longer Reasoning Help? Predicting Mathematical Reasoning Through Discovery and Execution](https://mlsanity.com/paper/2610.05322/) (2026)

## Abstract (arXiv)

Test-time scaling (TTS) has been shown to improve the performance of large language models (LLMs) by sampling and aggregating diverse reasoning paths. However, existing research has overlooked a critical issue: selection bias of reasoning strategies during scaling. Specifically, when generating reasoning processes, LLMs tend to follow certain strategies (e.g., algebraic solutions for math problems) while neglecting other valid alternatives (e.g., geometric solutions), resulting in insufficient exploration of the solution space. To further understand the impact of this bias, we present a theoretical analysis that reveals when it undermines the effectiveness of test-time scaling. Motivated by this theoretical insight, we introduce TTS-Uniform, a framework designed to mitigate the selection bias of reasoning strategies. It (i) identifies potential strategies, (ii) uniformly allocates the sampling budget across them, and (iii) filters out unstable strategies prior to aggregation. Experimental results show that TTS-Uniform significantly enhances scaling effectiveness across multiple mainstream LLMs and benchmark datasets.