# Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning

arXiv: https://arxiv.org/abs/2503.07065 · HTML: https://mlsanity.com/paper/2503.07065/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 40 of its 49 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 40)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [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)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models](https://mlsanity.com/paper/2305.07895/) (2023)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)

## Built on by (most cited first, 30 of 71)

- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models](https://mlsanity.com/paper/2504.11468/) (2025)
- [Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2503.12605/) (2025)
- [ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models](https://mlsanity.com/paper/2505.21500/) (2025)
- [Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models](https://mlsanity.com/paper/2505.04921/) (2025)
- [NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation](https://mlsanity.com/paper/2504.13055/) (2025)
- [More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models](https://mlsanity.com/paper/2505.21523/) (2025)
- [UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning](https://mlsanity.com/paper/2505.14231/) (2025)
- [SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward](https://mlsanity.com/paper/2505.17018/) (2025)
- [ZeroGUI: Automating Online GUI Learning at Zero Human Cost](https://mlsanity.com/paper/2505.23762/) (2025)
- [MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning](https://mlsanity.com/paper/2506.00555/) (2025)
- [Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles](https://mlsanity.com/paper/2505.23590/) (2025)
- [VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models](https://mlsanity.com/paper/2509.19803/) (2025)
- [EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning](https://mlsanity.com/paper/2505.04623/) (2025)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2506.07905/) (2025)
- [MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval](https://mlsanity.com/paper/2506.12364/) (2025)
- [Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation](https://mlsanity.com/paper/2505.08364/) (2025)
- [EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT](https://mlsanity.com/paper/2510.23569/) (2025)
- [Co-Reinforcement Learning for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2505.17534/) (2025)
- [TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs](https://mlsanity.com/paper/2509.18056/) (2025)
- [GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning](https://mlsanity.com/paper/2509.25026/) (2025)
- [Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models](https://mlsanity.com/paper/2505.18536/) (2025)
- [ChartReasoner: Code-Driven Modality Bridging for Long-Chain Reasoning in Chart Question Answering](https://mlsanity.com/paper/2506.10116/) (2025)
- [GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learning](https://mlsanity.com/paper/2507.23581/) (2025)
- [CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs](https://mlsanity.com/paper/2602.03048/) (2026)
- [Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning](https://mlsanity.com/paper/2507.00748/) (2025)
- [ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Models](https://mlsanity.com/paper/2512.06328/) (2025)
- [CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.00568/) (2025)

## Abstract (arXiv)

While state-of-the-art vision-language models (VLMs) have demonstrated remarkable capabilities in complex visual-text tasks, their success heavily relies on massive model scaling, limiting their practical deployment. Small-scale VLMs offer a more practical alternative but face significant challenges when trained with traditional supervised fine-tuning (SFT), particularly in two aspects: out-of-domain (OOD) generalization and reasoning abilities, which significantly lags behind the contemporary Large language models (LLMs). To address these challenges, we propose Curriculum Reinforcement Finetuning (Curr-ReFT), a novel post-training paradigm specifically designed for small-scale VLMs. Inspired by the success of reinforcement learning in LLMs, Curr-ReFT comprises two sequential stages: (1) Curriculum Reinforcement Learning, which ensures steady progression of model capabilities through difficulty-aware reward design, transitioning from basic visual perception to complex reasoning tasks; and (2) Rejected Sampling-based Self-improvement, which maintains the fundamental capabilities of VLMs through selective learning from high-quality multimodal and language examples. Extensive experiments demonstrate that models trained with Curr-ReFT paradigm achieve state-of-the-art performance across various visual tasks in both in-domain and out-of-domain settings. Moreover, our Curr-ReFT enhanced 3B model matches the performance of 32B-parameter models, demonstrating that efficient training paradigms can effectively bridge the gap between small and large models.