# Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning

arXiv: https://arxiv.org/abs/2508.10019 · HTML: https://mlsanity.com/paper/2508.10019/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 37 of its 55 references that are in the map.
- First posted on arXiv 7 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 37)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023)
- [GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models](https://mlsanity.com/paper/2410.05229/) (2024)
- [The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models](https://mlsanity.com/paper/2505.22617/) (2025)
- [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://mlsanity.com/paper/2004.02984/) (2020)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://mlsanity.com/paper/2501.04519/) (2025)
- [Evaluating the Performance of Large Language Models on GAOKAO Benchmark](https://mlsanity.com/paper/2305.12474/) (2023)
- [Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves](https://mlsanity.com/paper/2311.04205/) (2023)
- [Small Models Struggle to Learn from Strong Reasoners](https://mlsanity.com/paper/2502.12143/) (2025)
- [Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning](https://mlsanity.com/paper/2412.09078/) (2024)
- [Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning](https://mlsanity.com/paper/2507.00432/) (2025)
- [On-Device Language Models: A Comprehensive Review](https://mlsanity.com/paper/2409.00088/) (2024)
- [BOND: Aligning LLMs with Best-of-N Distillation](https://mlsanity.com/paper/2407.14622/) (2024)
- [LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning](https://mlsanity.com/paper/2007.08124/) (2020)
- [Do Large Language Model Benchmarks Test Reliability?](https://mlsanity.com/paper/2502.03461/) (2025)
- [Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search](https://mlsanity.com/paper/2502.02508/) (2025)
- [TEMPERA: Test-Time Prompting via Reinforcement Learning](https://mlsanity.com/paper/2211.11890/) (2022)

## Built on by (most cited first, 1 of 1)

- [Learning What to Learn: Stage-Specific Data Sets for SFT-then-RL in Small Language Model Reasoning](https://mlsanity.com/paper/2606.04466/) (2026)

## Abstract (arXiv)

Despite recent advances in the reasoning capabilities of Large Language Models (LLMs), improving the reasoning ability of Small Language Models (SLMs, e.g., up to 1.5B parameters) remains challenging. A key obstacle lies in the complexity and variability of natural language: essentially equivalent problems often appear in diverse surface forms, often obscured by redundant or distracting details. This imposes a dual burden on SLMs: they must first extract the core problem from complex linguistic input, and then perform reasoning based on that understanding. The resulting vast and noisy problem space hinders optimization, particularly for models with limited capacity. To address this, we propose a new framework that decouples understanding from reasoning by mapping natural language problems into a canonical problem space-a semantically simplified yet expressive domain. This enables SLMs to focus on reasoning over standardized inputs, free from linguistic variability. Within this framework, we introduce DURIT (Decoupled Understanding from Reasoning via Iterative Training), a three-step algorithm that iteratively: (1) mapping natural language problems via reinforcement learning, (2) aligns reasoning trajectories through self-distillation, and (3) trains reasoning policies in the problem space. The mapper and reasoner are co-trained in an alternating loop throughout this process. Experiments show that DURIT substantially improves SLMs' performance on both in-domain and out-of-domain mathematical and logical reasoning tasks. Beyond improving reasoning capabilities, DURIT also improves the robustness of reasoning, validating decoupling understanding from reasoning as an effective strategy for strengthening SLMs.