# Boosting MLLM Reasoning with Text-Debiased Hint-GRPO

arXiv: https://arxiv.org/abs/2503.23905 · HTML: https://mlsanity.com/paper/2503.23905/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 30 of its 39 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 30 of 30)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [Are We on the Right Way for Evaluating Large Vision-Language Models?](https://mlsanity.com/paper/2403.20330/) (2024)
- [MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?](https://mlsanity.com/paper/2403.14624/) (2024)
- [HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models](https://mlsanity.com/paper/2310.14566/) (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)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?](https://mlsanity.com/paper/2407.01284/) (2024)
- [G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model](https://mlsanity.com/paper/2312.11370/) (2023)
- [Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search](https://mlsanity.com/paper/2412.18319/) (2024)
- [LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs](https://mlsanity.com/paper/2501.06186/) (2025)
- [Improve Vision Language Model Chain-of-thought Reasoning](https://mlsanity.com/paper/2410.16198/) (2024)
- [Virgo: A Preliminary Exploration on Reproducing o1-like MLLM](https://mlsanity.com/paper/2501.01904/) (2025)
- [AI2D-RST: A multimodal corpus of 1000 primary school science diagrams](https://mlsanity.com/paper/1912.03879/) (2019)
- [MM-MATH: Advancing Multimodal Math Evaluation with Process Evaluation and Fine-grained Classification](https://mlsanity.com/paper/2404.05091/) (2024)
- [Diving into Self-Evolving Training for Multimodal Reasoning](https://mlsanity.com/paper/2412.17451/) (2024)
- [Progressive Multimodal Reasoning via Active Retrieval](https://mlsanity.com/paper/2412.14835/) (2024)

## Built on by (most cited first, 30 of 32)

- [DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO](https://mlsanity.com/paper/2506.07464/) (2025)
- [Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle](https://mlsanity.com/paper/2509.16679/) (2025)
- [Nudging the Boundaries of LLM Reasoning](https://mlsanity.com/paper/2509.25666/) (2025)
- [RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning](https://mlsanity.com/paper/2505.17540/) (2025)
- [Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning](https://mlsanity.com/paper/2511.18437/) (2025)
- [Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model](https://mlsanity.com/paper/2505.19406/) (2025)
- [AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video](https://mlsanity.com/paper/2508.03100/) (2025)
- [ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning](https://mlsanity.com/paper/2512.13095/) (2025)
- [MAPO: Mixed Advantage Policy Optimization](https://mlsanity.com/paper/2509.18849/) (2025)
- [Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning](https://mlsanity.com/paper/2601.18984/) (2026)
- [G2RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance](https://mlsanity.com/paper/2508.13023/) (2025)
- [No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning](https://mlsanity.com/paper/2601.06794/) (2026)
- [KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance](https://mlsanity.com/paper/2604.12627/) (2026)
- [Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It](https://mlsanity.com/paper/2606.26027/) (2026)
- [EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2602.23802/) (2026)
- [A Survey of Deep Learning for Geometry Problem Solving](https://mlsanity.com/paper/2507.11936/) (2025)
- [Learning Agentic Policy from Action Guidance](https://mlsanity.com/paper/2605.12004/) (2026)
- [DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant Advantage](https://mlsanity.com/paper/2603.01106/) (2026)
- [Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems](https://mlsanity.com/paper/2607.07674/) (2026)
- [GCPO: When Contrast Fails, Go Gold](https://mlsanity.com/paper/2510.07790/) (2025)
- [Topo-R1: Detecting Topological Anomalies via Vision-Language Models](https://mlsanity.com/paper/2603.13054/) (2026)
- [MHPR: Multidimensional Human Perception and Reasoning Benchmark for Large Vision-Languate Models](https://mlsanity.com/paper/2605.03485/) (2026)
- [Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime](https://mlsanity.com/paper/2605.05112/) (2026)
- [ViRC: Enhancing Visual Interleaved Mathematical CoT with Reason Chunking](https://mlsanity.com/paper/2512.14654/) (2025)
- [CheXPO-v2: Preference Optimization for Chest X-ray VLMs with Knowledge Graph Consistency](https://mlsanity.com/paper/2512.17213/) (2025)
- [MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learning](https://mlsanity.com/paper/2603.16929/) (2026)
- [DiagramNet: An End-to-End Recognition Framework and Dataset for Non-Standard System-Level Diagrams](https://mlsanity.com/paper/2605.01338/) (2026)
- [MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning](https://mlsanity.com/paper/2606.17888/) (2026)
- [The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms](https://mlsanity.com/paper/2606.25450/) (2026)
- [Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning](https://mlsanity.com/paper/2607.08572/) (2026)

## Abstract (arXiv)

MLLM reasoning has drawn widespread research for its excellent problem-solving capability. Current reasoning methods fall into two types: PRM, which supervises the intermediate reasoning steps, and ORM, which supervises the final results. Recently, DeepSeek-R1 has challenged the traditional view that PRM outperforms ORM, which demonstrates strong generalization performance using an ORM method (i.e., GRPO). However, current MLLM's GRPO algorithms still struggle to handle challenging and complex multimodal reasoning tasks (e.g., mathematical reasoning). In this work, we reveal two problems that impede the performance of GRPO on the MLLM: Low data utilization and Text-bias. Low data utilization refers to that GRPO cannot acquire positive rewards to update the MLLM on difficult samples, and text-bias is a phenomenon that the MLLM bypasses image condition and solely relies on text condition for generation after GRPO training. To tackle these problems, this work proposes Hint-GRPO that improves data utilization by adaptively providing hints for samples of varying difficulty, and text-bias calibration that mitigates text-bias by calibrating the token prediction logits with image condition in test-time. Experiment results on three base MLLMs across eleven datasets demonstrate that our proposed methods advance the reasoning capability of original MLLM by a large margin, exhibiting superior performance to existing MLLM reasoning methods. Our code is available at https://github.com/hqhQAQ/Hint-GRPO.