# Mode-Conditioning Unlocks Superior Test-Time Scaling

arXiv: https://arxiv.org/abs/2512.01127 · HTML: https://mlsanity.com/paper/2512.01127/

## Key facts

- Cited by 8 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 9 of its 47 references that are in the map.
- First posted on arXiv 30 Nov 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, 9 of 9)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [LESS: Selecting Influential Data for Targeted Instruction Tuning](https://mlsanity.com/paper/2402.04333/) (2024)
- [OpenThoughts: Data Recipes for Reasoning Models](https://mlsanity.com/paper/2506.04178/) (2025)
- [Stream of Search (SoS): Learning to Search in Language](https://mlsanity.com/paper/2404.03683/) (2024)
- [Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models](https://mlsanity.com/paper/2508.10751/) (2025)
- [Best-of-N Jailbreaking](https://mlsanity.com/paper/2412.03556/) (2024)
- [On the Effect of Sampling Diversity in Scaling LLM Inference](https://mlsanity.com/paper/2502.11027/) (2025)

## Built on by (most cited first, 8 of 8)

- [Expanding LLM Agent Boundaries with Strategy-Guided Exploration](https://mlsanity.com/paper/2603.02045/) (2026)
- [Beyond Consensus: Trace-Level Synthesis in Mixture of Agents](https://mlsanity.com/paper/2605.29116/) (2026)
- [No Single Best Model for Diversity: Learning a Router for Sample Diversity](https://mlsanity.com/paper/2604.02319/) (2026)
- [Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning](https://mlsanity.com/paper/2601.23027/) (2026)
- [Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2609.14896/) (2026)
- [Gradient Atoms: Unsupervised Discovery, Attribution and Steering of Model Behaviors via Sparse Decomposition of Training Gradients](https://mlsanity.com/paper/2603.14665/) (2026)
- [Characterizing a Configuration Where Inference-Time PRM-Pruned Fragment Grafting Is Inert: Evidence from Three Reasoning LMs](https://mlsanity.com/paper/2610.00047/) (2026)
- [Gacha Decoding: Eliciting Diverse Generations Through Instruction Following](https://mlsanity.com/paper/2610.01382/) (2026)

## Abstract (arXiv)

Parallel sampling promises substantial gains in test-time scaling, but its effectiveness is sharply limited by diversity collapse, where models concentrate on a few modes and repeated samples produce the same mistakes. We propose the mode-conditioning (ModC) framework, which explicitly allocates test-time compute across reasoning modes using either specialist models or mode-specific prefixes. ModC consistently improves scaling across controlled graph-search tasks and large-scale reasoning benchmarks, spanning model families and sizes from 0.5B to 7B. On OpenThoughts, fine-tuning Qwen2.5-7B with ModC achieves a 4x efficiency gain over standard training while also improving the maximum attainable Pass@k. We further show that gradient clustering enables ModC without explicit mode labels, yielding up to 10% gains on datasets such as NuminaMath. Finally, we show that ModC improves reinforcement learning (RL) and can further boost diversity-inducing RL methods. These results demonstrate that standard training underutilizes the diversity in data, and that ModC provides a simple, effective remedy for unlocking the full benefits of diversity in test-time scaling.