arXiv AI
IMAGAgent: Orchestrating Multi-Turn Image Editing via Constraint-Aware Planning and Reflection
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 10
Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing
arXiv:2607. 08497v1 Announce Type: cross Abstract: Recent unified multimodal models show a single architecture can jointly perform vision/language understanding and image generation/editing.
Hugging Face Trending Papers
Jun 11
InterleaveThinker: Reinforcing Agentic Interleaved Generation
Recent image generators have demonstrated impressive photorealism and instruction-following capabilities in single-image generation and editing. However, constrained by their architectures, they cannot achieve interleaved generation (text-image sequence), which has crucial applications in visual narratives, guidance, and embodied manipulation.
arXiv Computation and Language
Aug 27
VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following
VISA (Visual Instruction Synthesis Agent) is an agentic framework that transforms multimodal instruction synthesis into a self‑evolving loop. Each cycle analyzes images to filter constraints, samples new constraint sets, generates candidate instructions, and verifies them using executable tools and large language model judges. Failed samples trigger diagnostic recovery, while accepted samples are evaluated against the target model to estimate difficulty, with all feedback written back to memory to adapt future rounds and provide reward signals for reinforcement learning.
arXiv AI
Jun 6
Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing
arXiv:2606. 05950v1 Announce Type: new Abstract: Text-guided image editing has advanced rapidly with diffusion models and unified multimodal foundation models.
arXiv Computer Vision
Oct 12
Stride: Scale-Aware Multi-Agent Evolutionary Refinement for Infographic Generation
Stride is a multi‑agent framework for infographic generation that separates constraint evaluation from visual grounding, routing global revisions to a composer subagent and local corrections to a retoucher subagent. Each subagent plans internally and produces multiple candidates, and Stride accepts only those that improve a verifier score, thereby preventing regression across iterations. This scale‑aware, redundancy‑rich approach yields stable improvement and outperforms proprietary systems on several benchmarks, achieving state‑of‑the‑art results on WISE and strong performance on BizGenEval and IGenBench.
arXiv AI
Jun 2
CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences
arXiv:2606. 00931v1 Announce Type: cross Abstract: Instruction-guided image editing is becoming a general interface for visual work, yet existing benchmarks still focus largely on narrow appearance edits and do not fully capture the diversity of real-image tasks in professional workflows.