Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing
Text-guided image editing has advanced rapidly with diffusion models and unified multimodal foundation models. However, most existing methods remain confined to single-turn settings, overlooking the more realistic scenario of multi-turn in-context editing, where users iteratively refine an image through a sequence of instructions. In this setting, a model must follow each new instruction while preserving accumulated session-level constraints, challenged by two coupled failure modes: long-context dilution, where sparse textual constraints become difficult to recover from growing interleaved image-text histories, and state contamination, where earlier editing mistakes degrade subsequent generations. We introduce Edit-R2, a novel reinforcement learning post-training framework for unified multimodal models. Edit-R2 reconstructs the operative session intent, which effectively consolidates scattered historical constraints into an explicit reasoning trace before each editing turn. It further enables multi-turn RL over both reasoning and generation through a unified objective that jointly optimizes intent reconstruction generation in discrete text space and flow-matching image generation in continuous latent space, while a trajectory filtering mechanism suppresses corrupted rollouts to stabilize training under state contamination. To support systematic evaluation, we introduce MICE-Bench, a large-scale benchmark for multi-turn in-context editing with automated metrics for instruction following (IF), content consistency (CC), and global awareness (GA) over accumulated session constraints. Experiments show that Edit-R2 substantially improves multi-turn in-context editing and achieves competitive performance compared against strong baselines.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningInstruction FollowingImage GenerationImage EditingSimilar Papers 제목 키워드 기반
ChartEditBench: Evaluating Grounded Multi-Turn Chart Editing in Multimodal Language Models
While Multimodal Large Language Models (MLLMs) perform strongly on single-turn chart generation, their ability to support real-world exploratory data analysis remains underexplored. In practice, users iteratively refine …
Not All Turns Matter: Credit Assignment for Multi-Turn Jailbreaking
Deploying LLMs in multi-turn dialogues facilitates jailbreak attacks that distribute harmful intent across seemingly benign turns. Recent training-based multi-turn jailbreak methods learn long-horizon attack strategies f…
Reinforcement LearningTAMTRL: Teacher-Aligned Reward Reshaping for Multi-Turn Reinforcement Learning in Long-Context Compression
The rapid progress of large language models (LLMs) has led to remarkable performance gains across a wide range of tasks. However, when handling long documents that exceed the model's context window limit, the entire cont…
Reinforcement LearningMICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue
Reinforcement learning (RL) for large language models (LLMs) has shown strong performance in single-turn tasks, but extending it to multi-turn interaction remains challenging due to sparse rewards and poor per-turn credi…
Reinforcement LearningIMAGAgent: Orchestrating Multi-Turn Image Editing via Constraint-Aware Planning and Reflection
Existing multi-turn image editing paradigms are often confined to isolated single-step execution. Due to a lack of context-awareness and closed-loop feedback mechanisms, they are prone to error accumulation and semantic …
Image RetrievalImage Editing