# Learning Deliberately, Acting Intuitively: Unlocking Test-Time Reasoning in Multimodal LLMs

arXiv: https://arxiv.org/abs/2507.06999 · HTML: https://mlsanity.com/paper/2507.06999/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 9 Jul 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 22 of 22)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset](https://mlsanity.com/paper/2402.14804/) (2024)
- [LLaVA-CoT: Let Vision Language Models Reason Step-by-Step](https://mlsanity.com/paper/2411.10440/) (2024)
- [R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization](https://mlsanity.com/paper/2503.12937/) (2025)
- [Reasoning with Exploration: An Entropy Perspective](https://mlsanity.com/paper/2506.14758/) (2025)
- [The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning](https://mlsanity.com/paper/2312.01552/) (2023)
- [Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement](https://mlsanity.com/paper/2503.06520/) (2025)
- [Towards Complex Document Understanding By Discrete Reasoning](https://mlsanity.com/paper/2207.11871/) (2022)
- [Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs](https://mlsanity.com/paper/2404.15676/) (2024)
- [ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing](https://mlsanity.com/paper/2505.11935/) (2025)
- [Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking](https://mlsanity.com/paper/2501.01306/) (2025)
- [Boosting LLM Reasoning via Spontaneous Self-Correction](https://mlsanity.com/paper/2506.06923/) (2025)
- [Think Fast, Think Slow, Think Critical: Designing an Automated Propaganda Detection Tool](https://mlsanity.com/paper/2402.19135/) (2024)
- [DSADF: Thinking Fast and Slow for Decision Making](https://mlsanity.com/paper/2505.08189/) (2025)
- [Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs](https://mlsanity.com/paper/2305.01938/) (2023)

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

- [Guiding Perception-Reasoning Closer to Human in Blind Image Quality Assessment](https://mlsanity.com/paper/2512.16484/) (2025)

## Abstract (arXiv)

Reasoning is essential for large language models (LLMs), especially in complex tasks such as mathematical problem solving. However, multimodal reasoning still faces challenges in modality alignment and training scalability, as many existing methods rely on additional annotations or complex rule-based rewards. To address these issues, we propose the Deliberate-to-Intuitive reasoning framework (D2I), which improves the understanding and reasoning abilities of multimodal LLMs (MLLMs) without extra annotations or complex rewards. During training, D2I uses deliberate reasoning strategies supervised only by rule-based format rewards to enhance modality alignment. During inference, it shifts to intuitive reasoning by removing these explicit strategies, allowing the model to implicitly apply the acquired abilities in its responses. D2I outperforms baselines on both in-domain and out-of-domain benchmarks, highlighting the effectiveness of format rewards in fostering transferable multimodal reasoning skills and suggesting the benefit of decoupling training-time reasoning depth from test-time response flexibility.