# EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing

arXiv: https://arxiv.org/abs/2509.13399 · HTML: https://mlsanity.com/paper/2509.13399/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 44 of its 54 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 44)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [Step1X-Edit: A Practical Framework for General Image Editing](https://mlsanity.com/paper/2504.17761/) (2025)
- [OmniGen: Unified Image Generation](https://mlsanity.com/paper/2409.11340/) (2024)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [Emu Edit: Precise Image Editing via Recognition and Generation Tasks](https://mlsanity.com/paper/2311.10089/) (2023)
- [SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models](https://mlsanity.com/paper/2406.01584/) (2024)
- [UltraEdit: Instruction-based Fine-Grained Image Editing at Scale](https://mlsanity.com/paper/2407.05282/) (2024)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [OmniGen2: Towards Instruction-Aligned Multimodal Generation](https://mlsanity.com/paper/2506.18871/) (2025)
- [AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea](https://mlsanity.com/paper/2411.15738/) (2024)
- [ImgEdit: A Unified Image Editing Dataset and Benchmark](https://mlsanity.com/paper/2505.20275/) (2025)
- [HPSv3: Towards Wide-Spectrum Human Preference Score](https://mlsanity.com/paper/2508.03789/) (2025)

## Built on by (most cited first, 10 of 10)

- [Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation](https://mlsanity.com/paper/2602.03595/) (2026)
- [FreqEdit: Preserving High-Frequency Features for Robust Multi-Turn Image Editing](https://mlsanity.com/paper/2512.01755/) (2025)
- [LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation](https://mlsanity.com/paper/2604.11789/) (2026)
- [HarnessEval-W: Agentifying the Evaluation of Visual Worlds](https://mlsanity.com/paper/2608.16859/) (2026)
- [Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space](https://mlsanity.com/paper/2605.08250/) (2026)
- [Open Evaluation Agent: Efficient and Promptable Evaluation of Visual Generative Models](https://mlsanity.com/paper/2608.09666/) (2026)
- [MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching](https://mlsanity.com/paper/2606.01985/) (2026)
- [Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing](https://mlsanity.com/paper/2606.05950/) (2026)
- [Rethinking Where to Edit: Task-Aware Localization for Instruction-Based Image Editing](https://mlsanity.com/paper/2604.20258/) (2026)
- [Do MLLM Judges Judge the Edit? Auditing Bias in Image Editing Evaluation with Verified Quality Preservation](https://mlsanity.com/paper/2610.01670/) (2026)

## Abstract (arXiv)

Instruction-based image editing has advanced rapidly, yet reliable and interpretable evaluation remains a bottleneck. Current protocols either (i) depend on paired reference images, resulting in limited coverage and inheriting biases from prior generative models or (ii) rely solely on zero-shot vision language models (VLMs), whose prompt-based assessments of instruction following, content consistency, and visual quality are often imprecise. To address this, we introduce EdiVal, an automated and fine-grained evaluation framework grounded in an object-centric perspective, designed to assess not only standard single-turn but also multi-turn instruction-based editing with precision. Given an input image, EdiVal first decomposes it into semantically meaningful objects, then synthesizes diverse, context-aware editing instructions while dynamically updating object pools across turns. These two stages enable two novel object centric metrics tailored for multi turn evaluation and one global metric of visual quality: 1) EdiVal-IF, which measures instruction following by combining open vocabulary object detectors for symbolic checks with VLMs for semantic verification on detector guided crops; 2) EdiVal-CC, which evaluates content consistency by calculating semantic similarity of unchanged objects and background using the evolving object pools; and 3) EdiVal-VQ, which quantifies changes in overall visual quality with human preference models. Instantiating this pipeline, we build EdiVal Bench, a multi-turn editing benchmark covering 9 instruction types and 16 state-of-the-art editing models, spanning in-context, flow-matching, and diffusion paradigms. We demonstrate that EdiVal can be used to identify existing failure modes, thereby informing the development of the next generation of editing models.