# DataEvolver: Let Your Data Build and Improve Itself via Goal-Driven Loop Agents

arXiv: https://arxiv.org/abs/2605.01789 · HTML: https://mlsanity.com/paper/2605.01789/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 3 May 2026.

## Builds on (most cited first, 17 of 17)

- [Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details](https://mlsanity.com/paper/2506.16504/) (2025)
- [Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets](https://mlsanity.com/paper/2505.07747/) (2025)
- [Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing](https://mlsanity.com/paper/2510.19808/) (2025)
- [UniREditBench: A Unified Reasoning-based Image Editing Benchmark](https://mlsanity.com/paper/2511.01295/) (2025)
- [Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets](https://mlsanity.com/paper/2510.19944/) (2025)
- [PICABench: How Far Are We from Physically Realistic Image Editing?](https://mlsanity.com/paper/2510.17681/) (2025)
- [SPATIALGEN: Layout-guided 3D Indoor Scene Generation](https://mlsanity.com/paper/2509.14981/) (2025)
- [Image Editing As Programs with Diffusion Models](https://mlsanity.com/paper/2506.04158/) (2025)
- [GeoRemover: Removing Objects and Their Causal Visual Artifacts](https://mlsanity.com/paper/2509.18538/) (2025)
- [PartEdit: Fine-Grained Image Editing using Pre-Trained Diffusion Models](https://mlsanity.com/paper/2502.04050/) (2025)
- [Beyond Textual CoT: Interleaved Text-Image Chains with Deep Confidence Reasoning for Image Editing](https://mlsanity.com/paper/2510.08157/) (2025)
- [Advancing high-fidelity 3D and Texture Generation with 2.5D latents](https://mlsanity.com/paper/2505.21050/) (2025)
- [Cora: Correspondence-aware image editing using few step diffusion](https://mlsanity.com/paper/2505.23907/) (2025)
- [ZeroScene: A Zero-Shot Framework for 3D Scene Generation from a Single Image and Controllable Texture Editing](https://mlsanity.com/paper/2509.23607/) (2025)
- [I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing](https://mlsanity.com/paper/2601.03741/) (2026)
- [POEM: Precise Object-level Editing via MLLM control](https://mlsanity.com/paper/2504.08111/) (2025)
- [A Scalable Attention-Based Approach for Image-to-3D Texture Mapping](https://mlsanity.com/paper/2509.05131/) (2025)

## Abstract (arXiv)

Constructing controllable visual data is a major bottleneck for image editing and multimodal understanding. Useful supervision is rarely produced by a single rendering pass; instead it emerges through iterative generation, inspection, correction, filtering, and export. We present DataEvolver, a closed-loop visual data engine that organizes this process around explicit goals, persistent artifacts, bounded corrective actions, and acceptance decisions. DataEvolver supports multiple artifact types, including RGB images, masks, depth maps, normal maps, meshes, poses, trajectories, and review traces. In the current release, the system operates through two coupled loops: generation-time self-correction within each sample and validation-time self-expansion across dataset rounds. We validate the framework on an image-level object-rotation setting. With a fixed Qwen-Edit LoRA probe, our final Ours+DualGate model outperforms both the unadapted base model and a public multi-angle LoRA on SpatialEdit and a held-out evaluation set. Ablations show a consistent improvement path from scene-aware generation to feedback-driven correction and dual-gated validation. Beyond the released rotation data, our main contribution is a reusable framework for building visual datasets through explicit goal tracking, review, correction, and acceptance loops.