JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization

• URL: http://arxiv.org/abs/2511.23002v2
• Date: Thu, 04 Dec 2025 14:58:22 GMT
• Title: JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization
• Abstract summary: JarvisEvo is a unified image editing agent that emulates an expert human designer by iteratively editing, selecting appropriate tools, evaluating results, and reflecting on its own decisions to refine outcomes.<n>On ArtEdit-Bench, JarvisEvo outperforms Nano-Banana by an average of 18.95% on preservative editing metrics, including a substantial 44.96% improvement in pixel-level content fidelity.
• Score: 39.107071937105395
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agent-based editing models have substantially advanced interactive experiences, processing quality, and creative flexibility. However, two critical challenges persist: (1) instruction hallucination, text-only chain-of-thought (CoT) reasoning cannot fully prevent factual errors due to inherent information bottlenecks; (2) reward hacking, dynamic policy optimization against static reward models allows agents to exploit flaws in reward functions. To address these issues, we propose JarvisEvo, a unified image editing agent that emulates an expert human designer by iteratively editing, selecting appropriate tools, evaluating results, and reflecting on its own decisions to refine outcomes. JarvisEvo offers three key advantages: (1) an interleaved multimodal chain-of-thought (iMCoT) reasoning mechanism that enhances instruction following and editing quality; (2) a synergistic editor-evaluator policy optimization (SEPO) framework that enables self-improvement without external rewards, effectively mitigating reward hacking; and (3) support for both global and local fine-grained editing through seamless integration of Adobe Lightroom. On ArtEdit-Bench, JarvisEvo outperforms Nano-Banana by an average of 18.95% on preservative editing metrics, including a substantial 44.96% improvement in pixel-level content fidelity. Project page: https://jarvisevo.vercel.app/

Related papers

• IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment [16.199788035961564]
  We propose IEA, a conversational Image Editing Agent that learns to operate parameterized tools in an explicit, interpretable action space.<n>IEA is trained via a three-stage multitask pipeline: SFT on distilled expert edits, GRPO with rewards for likeness improvement, tool usefulness, and intent summarization, and (3) large-scale synthetic fine-tuning to jointly master image editing, refinement, and user intent summarization.
  arXiv  Detail & Related papers  (2026-06-06T07:11:08Z)
• When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editing [61.80513991207956]
  We introduce SPPE (Surrogate-based Privacy-Preserving Editing), the first recovery-oriented benchmark covering 36 fine-grained privacy categories and 65 editing instructions.<n>For editability assessment, ERMA improves over the best-performing baselines by 13.9% in SRCC and 12.3% in PLCC.<n>Experiments on SPPE and InstructPix2Pix show consistent improvements on both tasks.
  arXiv  Detail & Related papers  (2026-06-05T11:40:03Z)
• CoEditor++: Instruction-based Visual Editing via Cognitive Reasoning [98.98349220451216]
  CoEditor++ is a training-free framework that decomposes editing into "what to edit" and "how to edit"<n>We show that CoEditor++ achieves state-of-the-art performance in both general editing and responsible editing tasks.<n>Our findings suggest the potential toward cognitive-centric instruction-based image editing.
  arXiv  Detail & Related papers  (2026-01-31T12:20:46Z)
• CoreEditor: Consistent 3D Editing via Correspondence-constrained Diffusion [24.144486805878596]
  CoreEditor is a novel framework for consistent text-to-3D editing.<n>We introduce a correspondence-constrained attention mechanism that enforces precise interactions between pixels.<n>In experiments, CoreEditor produces high-quality, 3D-consistent edits with sharper details.
  arXiv  Detail & Related papers  (2025-08-15T17:13:11Z)
• LORE: Latent Optimization for Precise Semantic Control in Rectified Flow-based Image Editing [0.276240219662896]
  We introduce LORE, a training-free and efficient image editing method.<n>LORE directly optimize the inverted noise, addressing the core limitations in generalization and controllability of existing approaches.<n> Experimental results show that LORE significantly outperforms strong baselines in terms of semantic alignment, image quality, and background fidelity.
  arXiv  Detail & Related papers  (2025-08-05T06:45:04Z)
• JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent [74.64342043677975]
  Photo retouching has become integral to contemporary visual storytelling, enabling users to capture aesthetics and express creativity.<n>We introduce JarvisArt, a multi-modal language model (MLLM)-driven agent that understands user intent, mimics the reasoning process of professional artists, and intelligently coordinates over 200 retouching tools within Lightroom.<n>To evaluate performance, we develop MMArt-Bench, a novel benchmark constructed from real-world user edits.<n>JarvisArt outperforms GPT-4o with a 60% improvement in average pixel-level metrics on MMArt-Bench for content fidelity, while maintaining comparable instruction-following capabilities.
  arXiv  Detail & Related papers  (2025-06-21T06:36:00Z)
• Lost in Edits? A $λ$-Compass for AIGC Provenance [119.95562081325552]
  We propose a novel latent-space attribution method that robustly identifies and differentiates authentic outputs from manipulated ones.<n>LambdaTracer is effective across diverse iterative editing processes, whether automated through text-guided editing tools such as InstructPix2Pix or performed manually with editing software such as Adobe Photoshop.
  arXiv  Detail & Related papers  (2025-02-05T06:24:25Z)
• S3Editor: A Sparse Semantic-Disentangled Self-Training Framework for Face Video Editing [38.804508101698275]
  We introduce S3Editor, a Sparse Semantic-disentangled Self-training framework for face video editing. Firstly, S3Editor adopts a self-training paradigm to enhance the training process through semi-supervision. Secondly, we propose a semantic disentangled architecture with a dynamic routing mechanism that accommodates diverse editing requirements.
  arXiv  Detail & Related papers  (2024-04-11T20:25:26Z)
• Responsible Visual Editing [53.45295657891099]
  We formulate a new task, responsible visual editing, which entails modifying specific concepts within an image to render it more responsible while minimizing changes. To mitigate the negative implications of harmful images on research, we create a transparent and public dataset, AltBear, which expresses harmful information using teddy bears instead of humans. We find that the AltBear dataset corresponds well to the harmful content found in real images, offering a consistent experimental evaluation.
  arXiv  Detail & Related papers  (2024-04-08T14:56:26Z)
• Object-aware Inversion and Reassembly for Image Editing [61.19822563737121]
  We propose Object-aware Inversion and Reassembly (OIR) to enable object-level fine-grained editing. We use our search metric to find the optimal inversion step for each editing pair when editing an image. Our method achieves superior performance in editing object shapes, colors, materials, categories, etc., especially in multi-object editing scenarios.
  arXiv  Detail & Related papers  (2023-10-18T17:59:02Z)
• TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing [110.82128064489237]
  We propose TransEditor, a novel Transformer-based framework to enhance interaction in a dual-space GAN for more controllable editing. Experiments demonstrate the superiority of the proposed framework in image quality and editing capability, suggesting the effectiveness of TransEditor for highly controllable facial editing.
  arXiv  Detail & Related papers  (2022-03-31T17:58:13Z)

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.