RetouchIQ: MLLM Agents for Instruction-Based Image Retouching with Generalist Reward

arXiv:2602.17558 · cs.CV · Submitted 2026-02-19 · Read on arXiv

cs.CV

Submitted: 2026-02-19

Updated: 2026-02-19

Terminology

• Reinforcement Learning — 17× in this paper · explained in 4 episodes
• Generalist Reward Model — 13× in this paper
• Benchmark — 11× in this paper · explained in 2 episodes
• Fine-Tuning — 11× in this paper · explained in 5 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Consistency — 7× in this paper · explained in 3 episodes
• Policy-Guided Reward Training — 5× in this paper
• Alignment — 4× in this paper · explained in 1 episode
• Reinforcement Learning (RL) — 4× in this paper · explained in 24 episodes
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Multimodal Reasoning — 3× in this paper · explained in 5 episodes
• Verifiable Rewards — 3× in this paper · explained in 2 episodes
• ACM Transactions on Graphics — 2× in this paper
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Distribution Shift — 2× in this paper · explained in 5 episodes
• Initial Data — 2× in this paper · explained in 2 episodes
• Reward Function — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Hybrid System — 1× in this paper · explained in 2 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Two-Stage Training Strategy — 1× in this paper · explained in 3 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes

Sources

• Qwen2.5-VL Technical Report
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Training-Free Large Model Priors for Multiple-in-One Image Restoration
• Prompt-to-Prompt Image Editing with Cross Attention Control
• GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration
• JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent
• Inference-Time Scaling for Generalist Reward Modeling
• UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning
• GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents
• We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning
• Skywork-R1V3 Technical Report
• Score-Based Generative Modeling through Stochastic Differential Equations
• VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
• VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning
• Generative RLHF-V: Learning Principles from Multi-modal Human Preference

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models