# VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning

arXiv: https://arxiv.org/abs/2508.06051 · HTML: https://mlsanity.com/paper/2508.06051/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 31 of its 52 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 30 of 31)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment](https://mlsanity.com/paper/1910.06180/) (2019)
- [Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives](https://mlsanity.com/paper/2211.04894/) (2022)
- [Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision](https://mlsanity.com/paper/2309.14181/) (2023)
- [FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling](https://mlsanity.com/paper/2207.02595/) (2022)
- [Quality Assessment of In-the-Wild Videos](https://mlsanity.com/paper/1908.00375/) (2019)
- [Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models](https://mlsanity.com/paper/2311.06783/) (2023)
- [Patch-VQ: 'Patching Up' the Video Quality Problem](https://mlsanity.com/paper/2011.13544/) (2020)
- [A Deep Learning based No-reference Quality Assessment Model for UGC Videos](https://mlsanity.com/paper/2204.14047/) (2022)
- [Large-Scale Study of Perceptual Video Quality](https://mlsanity.com/paper/1803.01761/) (2018)
- [YouTube UGC Dataset for Video Compression Research](https://mlsanity.com/paper/1904.06457/) (2019)
- [Q-Insight: Understanding Image Quality via Visual Reinforcement Learning](https://mlsanity.com/paper/2503.22679/) (2025)
- [Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception](https://mlsanity.com/paper/2108.08505/) (2021)
- [Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models](https://mlsanity.com/paper/2505.04921/) (2025)
- [VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank](https://mlsanity.com/paper/2505.14460/) (2025)
- [Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approach](https://mlsanity.com/paper/2305.12726/) (2023)
- [Perceptual Video Quality Assessment: A Survey](https://mlsanity.com/paper/2402.03413/) (2024)
- [Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMs](https://mlsanity.com/paper/2409.20063/) (2024)
- [Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models](https://mlsanity.com/paper/2307.13981/) (2023)
- [VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning](https://mlsanity.com/paper/2506.18564/) (2025)
- [Subjective and Objective Quality Assessment of High Frame Rate Videos](https://mlsanity.com/paper/2007.11634/) (2020)
- [VDPVE: VQA Dataset for Perceptual Video Enhancement](https://mlsanity.com/paper/2303.09290/) (2023)
- [Study of Subjective and Objective Quality Assessment of Mobile Cloud Gaming Videos](https://mlsanity.com/paper/2305.17260/) (2023)

## Built on by (most cited first, 10 of 10)

- [EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment](https://mlsanity.com/paper/2602.01173/) (2026)
- [AesRM: Improving Video Aesthetics with Expert-Level Feedback](https://mlsanity.com/paper/2604.28078/) (2026)
- [Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation](https://mlsanity.com/paper/2602.03892/) (2026)
- [Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement](https://mlsanity.com/paper/2604.16858/) (2026)
- [GameScope: A Multi-Attribute, Multi-Codec Benchmark Dataset for Gaming Video Quality Assessment](https://mlsanity.com/paper/2605.01272/) (2026)
- [VersusQ: Pairwise Margin Reasoning for Generalizable Video Quality Assessment](https://mlsanity.com/paper/2605.21130/) (2026)
- [LEIQ-Assessor: Multi-dimensional Quality Assessment of Low-light Enhanced Images via Multi-task Learning](https://mlsanity.com/paper/2606.29752/) (2026)
- [DroneIQA-VLE: Multi-Task Drone Image Quality Assessment via Vision-Language Ensemble](https://mlsanity.com/paper/2607.00416/) (2026)
- [CompressedVQA-AEV: Full-Reference and No-Reference Quality Assessment Models for Asymmetric Encoded Videos](https://mlsanity.com/paper/2607.04606/) (2026)
- [SemABR: Measuring Video Semantic Fidelity with Multimodal LLMs for Adaptive Bitrate Streaming](https://mlsanity.com/paper/2609.18075/) (2026)

## Abstract (arXiv)

Video quality assessment (VQA) aims to objectively quantify perceptual quality degradation in alignment with human visual perception. Despite recent advances, existing VQA models still suffer from two critical limitations: textitpoor generalization to out-of-distribution (OOD) videos and textitlimited explainability, which restrict their applicability in real-world scenarios. To address these challenges, we propose VQAThinker, a reasoning-based VQA framework that leverages large multimodal models (LMMs) with reinforcement learning to jointly model video quality understanding and scoring, emulating human perceptual decision-making. Specifically, we adopt group relative policy optimization (GRPO), a rule-guided reinforcement learning algorithm that enables reasoning over video quality under score-level supervision, and introduce three VQA-specific rewards: (1) a bell-shaped regression reward that increases rapidly as the prediction error decreases and becomes progressively less sensitive near the ground truth; (2) a pairwise ranking reward that guides the model to correctly determine the relative quality between video pairs; and (3) a temporal consistency reward that encourages the model to prefer temporally coherent videos over their perturbed counterparts. Extensive experiments demonstrate that VQAThinker achieves state-of-the-art performance on both in-domain and OOD VQA benchmarks, showing strong generalization for video quality scoring. Furthermore, evaluations on video quality understanding tasks validate its superiority in distortion attribution and quality description compared to existing explainable VQA models and LMMs. These findings demonstrate that reinforcement learning offers an effective pathway toward building generalizable and explainable VQA models solely with score-level supervision.