WeAgent-MMGenEdit: A Full-Stack Recipe for Multimodal Agentic Image Generation and Editing
- URL: http://arxiv.org/abs/2609.05171v1
- Date: Fri, 04 Sep 2026 14:12:03 GMT
- Title: WeAgent-MMGenEdit: A Full-Stack Recipe for Multimodal Agentic Image Generation and Editing
- Abstract summary: We present WeAgent-MMGenEdit, a full-stack recipe including a multimodal harness, a scalable data construction pipeline, a comprehensive benchmark, and post-training methods for the agent policy and image backend.<n>We first introduce WeAgent-Harness, a multimodal runtime with persistent evidence management and dedicated verification and integration tools that organize retrieved multimodal evidence into a dense carrier. Upon this, we develop a scalable pipeline for prompt synthesis and agentic trajectory collection, yielding 23K supervised trajectories and 14.7K RL tasks with three-layer verifiable checklists.
- Score: 51.8784267764917
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Image generation and editing models have advanced rapidly, yet remain unreliable when prompts require external world knowledge. Bounded and long-tail parametric knowledge prevents direct or reason-then-generate approaches from recovering the required facts and visual appearances. Existing agentic generation and editing methods mitigate this limitation with retrieval tools, yet remain constrained by insufficient visual verification, overloaded policy models, and weak integration of retrieved textual and visual evidence. To address these limitations, we present WeAgent-MMGenEdit, a full-stack recipe including a multimodal harness, a scalable data construction pipeline, a comprehensive benchmark, and post-training methods for the agent policy and image backend. We first introduce WeAgent-Harness, a multimodal runtime with persistent evidence management and dedicated verification and integration tools that organize retrieved multimodal evidence into a dense carrier. Upon this, we develop a scalable pipeline for prompt synthesis and agentic trajectory collection, yielding 23K supervised trajectories and 14.7K RL tasks with three-layer verifiable checklists. We further introduce WeBench-MMGenEdit, a bilingual benchmark covering both knowledge-intensive image generation and multi-image editing. Finally, a two-sided post-training recipe based on SFT and RL improves the agent policy and image backend. Together, WeAgent-MMGenEdit enables a 30B-total/3B-active policy to outperform similarly sized policy models and approach the performance of a 1T-parameter agent.
Related papers
- WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents [53.426679066400844]
We introduce WeAgent-Harness, a multimodal agentic harness that supports native text-vision interaction and runtime recovery.<n>We develop WeAgent-MMSearch, an integrated system spanning data construction, agentic post-training, and multimodal rollout.<n>We also introduce VisTarget-Bench, a 150-task human-verified benchmark that pairs each question with a held-out target image.
arXiv Detail & Related papers (2026-08-28T08:28:43Z) - ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation [57.673228074553414]
ToolArtist is a fully agentic image generation model obtained by post-training a Unified Multimodal Model (UMM)<n>We show that ToolArtist orchestrates reasoning, external tool use, and native image generation within one unified policy.<n> Experiments show that placing the entire open-world image-generation process under an agent policy consistently outperforms approaches with fixed pipelines.
arXiv Detail & Related papers (2026-08-05T04:26:19Z) - GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning [54.42973725693]
We introduce GenAgent, unifying visual understanding and generation through an agentic multimodal model.<n>GenAgent significantly boosts base generator(FLUX.1-dev) performance on GenEval++ and WISE.<n>Our framework demonstrates three key properties: 1) cross-tool generalization to generators with varying capabilities, 2) test-time scaling with consistent improvements across interaction rounds, and 3) task-adaptive reasoning that automatically adjusts to different tasks.
arXiv Detail & Related papers (2026-01-26T14:49:04Z) - Training Multi-Image Vision Agents via End2End Reinforcement Learning [51.81337984526068]
We propose IMAgent, an open-source vision agent trained via end-to-end reinforcement learning.<n>By leveraging a multi-agent system, we generate challenging and visually-rich multi-image QA pairs.<n>We develop two specialized tools for visual reflection and confirmation, allowing the model to proactively reallocate its attention to image content.
arXiv Detail & Related papers (2025-12-05T10:02:38Z) - ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generation [49.01601313084479]
ImAgent is a training-free unified multimodal agent that integrates reasoning, generation, and self-evaluation.<n>Experiments on image generation and editing tasks demonstrate that ImAgent consistently improves over the backbone.
arXiv Detail & Related papers (2025-11-14T17:00:29Z) - CompAgent: An Agentic Framework for Visual Compliance Verification [3.847341641557404]
Visual compliance verification is a critical yet underexplored problem in computer vision.<n>In this paper, we propose CompAgent, the first agentic framework for visual compliance verification.<n>A verification agent then integrates image, tool outputs, and policy context to perform multi-modal reasoning.
arXiv Detail & Related papers (2025-10-31T18:20:06Z)
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.