Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning
- URL: http://arxiv.org/abs/2503.20752v2
- Date: Thu, 27 Mar 2025 03:13:00 GMT
- Title: Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning
- Authors: Huajie Tan, Yuheng Ji, Xiaoshuai Hao, Minglan Lin, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang,
- Abstract summary: Visual reasoning abilities play a crucial role in understanding complex multimodal data.<n>Existing methods improve VLM reasoning via Chain-of-Thought supervised fine-tuning.<n>We propose Reason-RFT, a novel reinforcement fine-tuning framework.
- Score: 19.28434717501445
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Visual reasoning abilities play a crucial role in understanding complex multimodal data, advancing both domain-specific applications and artificial general intelligence (AGI). Existing methods improve VLM reasoning via Chain-of-Thought (CoT) supervised fine-tuning, using meticulously annotated training data to enhance visual reasoning capabilities. However, this training paradigm may lead to overfitting and cognitive rigidity, restricting the model's ability to transfer visual reasoning skills across domains and limiting its real-world applicability. To address these limitations, we propose Reason-RFT, a novel reinforcement fine-tuning framework that significantly enhances generalization capabilities in visual reasoning tasks. Reason-RFT introduces a two-phase training framework for visual reasoning: (1) Supervised Fine-Tuning (SFT) with curated Chain-of-Thought (CoT) data activates the reasoning potential of Vision-Language Models (VLMs), followed by (2) Group Relative Policy Optimization (GRPO)-based reinforcement learning that generates multiple reasoning-response pairs, significantly enhancing generalization in visual reasoning tasks. To evaluate Reason-RFT's visual reasoning capabilities, we reconstructed a comprehensive dataset spanning visual counting, structure perception, and spatial transformation. Experimental results demonstrate Reasoning-RFT's three key advantages: (1) Performance Enhancement: achieving state-of-the-art results across multiple tasks, outperforming most mainstream open-source and proprietary models; (2) Generalization Superiority: consistently maintaining robust performance across diverse tasks and domains, outperforming alternative training paradigms; (3) Data Efficiency: excelling in few-shot learning scenarios while surpassing full-dataset SFT baselines. Project website: https://tanhuajie.github.io/ReasonRFT
Related papers
- Direct Reasoning Optimization: LLMs Can Reward And Refine Their Own Reasoning for Open-Ended Tasks [6.881699020319577]
We propose Direct Reasoning Optimization (DRO), a reinforcement learning framework for fine-tuning Large Language Models (LLMs)<n>DRO is guided by a new reward signal: the Reasoning Reflection Reward (R3)<n>DRO consistently outperforms strong baselines while remaining broadly applicable across both open-ended and structured domains.
arXiv Detail & Related papers (2025-06-16T10:43:38Z) - Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
arXiv Detail & Related papers (2025-06-11T12:03:52Z) - Perceptual Decoupling for Scalable Multi-modal Reasoning via Reward-Optimized Captioning [78.17782197231325]
We propose a reasoning-guided reinforcement learning strategy that aligns the extractor's captioning behavior with the reasoning objective.<n> Experiments on multi-modal math and science benchmarks show that the proposed RACRO method achieves state-of-the-art average performance.
arXiv Detail & Related papers (2025-06-05T02:28:07Z) - Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model [39.58344147240552]
We investigate whether large vision-language models (VLMs) can compose capabilities across modalities or tasks under out-of-distribution conditions.<n>Our findings shed light on the current limitations of RL-based reasoning VLM training and provide actionable insights toward building models that reason compositionally across modalities and tasks.
arXiv Detail & Related papers (2025-05-26T01:42:38Z) - VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model [29.524164786422368]
Recently, DeepSeek R1 has shown that reinforcement learning can substantially improve the reasoning capabilities of Large Language Models (LLMs)
We investigate the extension of R1-style reinforcement learning to Vision-Language Models (VLMs)
We develop VLM-R1, a dedicated framework designed to harness RL for improving VLMs' performance on general vision-language tasks.
arXiv Detail & Related papers (2025-04-10T10:05:15Z) - Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 [53.894789613838654]
We introduce SEED-Bench-R1, a benchmark designed to evaluate post-training methods for MLLMs in video understanding.
It includes intricate real-world videos and complex everyday planning tasks in the format of multiple-choice questions.
Using Qwen2-VL-Instruct-7B as a base model, we compare RL with supervised fine-tuning (SFT)
Our detailed analysis reveals that RL enhances visual perception but often produces less coherent reasoning chains.
arXiv Detail & Related papers (2025-03-31T17:55:23Z) - OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement [91.88062410741833]
This study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs)<n>We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization.<n>OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrates the potential of our strategy for robust vision-language reasoning.
arXiv Detail & Related papers (2025-03-21T17:52:43Z) - R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization [26.757458496178437]
We introduce R1-Onevision, a multimodal reasoning model designed to bridge the gap between visual perception and deep reasoning.<n>We construct the R1-Onevision dataset which provides detailed, step-by-step multimodal reasoning annotations across diverse domains.<n>We further develop the R1-Onevision model through supervised fine-tuning and reinforcement learning to cultivate advanced reasoning.<n> Experimental results show that R1-Onevision achieves state-of-the-art performance, outperforming models such as GPT-4o and Qwen2.5-VL.
arXiv Detail & Related papers (2025-03-13T17:56:05Z) - Visual-RFT: Visual Reinforcement Fine-Tuning [75.20572976629646]
Reinforcement Fine-Tuning (RFT) in Large Reasoning Models like OpenAI o1 learns from feedback on its answers.<n>Visual-RFT further extends the application areas of RFT on visual tasks.
arXiv Detail & Related papers (2025-03-03T18:16:32Z) - Cognitive Paradigms for Evaluating VLMs on Visual Reasoning Task [3.2228025627337864]
Advancing machine visual reasoning requires a deeper understanding of how Vision-Language Models (VLMs) process and interpret complex visual patterns.<n>This work introduces a novel, cognitively-inspired evaluation framework to systematically analyze VLM reasoning on natural image-based Bongard Problems.
arXiv Detail & Related papers (2025-01-23T12:42:42Z) - DRIVINGVQA: Analyzing Visual Chain-of-Thought Reasoning of Vision Language Models in Real-World Scenarios with Driving Theory Tests [69.00444996464662]
We present DrivingVQA, a new benchmark derived from driving theory tests to evaluate visual chain-of-thought reasoning in complex real-world scenarios.<n>Our experiments reveal that open-source and proprietary LVLMs struggle with visual chain-of-thought reasoning under zero-shot settings.<n>We investigate training strategies that leverage relevant entities to improve visual reasoning.
arXiv Detail & Related papers (2025-01-08T18:31:16Z) - STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training [87.58996020705258]
Video Large Language Models (Video-LLMs) have recently shown strong derivation in basic video understanding tasks.<n>Video-LLMs struggle with compositional reasoning that requires multi-step explicit-temporal inference across object relations, interactions and events.<n>We propose STEP, a novel graph-guided self-training method that enables VideoLLMs to generate reasoning-rich finetuning data from any raw videos to improve itself.
arXiv Detail & Related papers (2024-11-29T11:54:55Z) - Improve Vision Language Model Chain-of-thought Reasoning [86.83335752119741]
Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness.
We show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses.
arXiv Detail & Related papers (2024-10-21T17:00:06Z) - Cantor: Inspiring Multimodal Chain-of-Thought of MLLM [83.6663322930814]
We argue that converging visual context acquisition and logical reasoning is pivotal for tackling visual reasoning tasks.
We propose an innovative multimodal CoT framework, termed Cantor, characterized by a perception-decision architecture.
Our experiments demonstrate the efficacy of the proposed framework, showing significant improvements in multimodal CoT performance.
arXiv Detail & Related papers (2024-04-24T17:59:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.