arXiv Computer Vision October 19, 2026 By Xuanyu Liu, Hongyan Feng, Miao Pan, Sunlai Chen, Lizhou Liang, Bing Sun, Wenqi Zhang, Xuhong Zhang

Scene-Designer: Learning Design Intelligence for Agentic 3D Scene Generation

Read the original on arXiv Computer Vision →

Scene-Designer is an agentic framework that learns design intelligence for generating 3D indoor scenes from natural language. It introduces two datasets—Scene-OTA-35K for design and error correction, and Scene-OTC-15K for quality critique—and a Critic-guided GRPO framework (Scene-GRPO) that refines design decisions. Experiments show that Scene-Designer outperforms existing methods in physical validity, functional correctness, and layout coherence, and that its learned Critic provides effective guidance during test time.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

agents

arXiv Computer Vision

Aug 25

DesignAgent3D: Interactive 3D Scene Editing via Designer-like Multimodal Reasoning

arXiv:2608.21438v1 Announce Type: new Abstract: Text guided 3D scene editing provides an intuitive interface for modifying reconstructed environments, but remains difficult because natural language d...

By Xiujin Liu, Tianyu Yang, Yilun Zhao, Xiangliang Zhang

agents multimodal benchmarks safety

arXiv AI

1d ago

GREP: Grounding Generated Room Evaluation in Principles

The paper introduces GREP, a framework for evaluating AI-generated furnished rooms that moves beyond specific questions to a three-tier philosophy: basic physical validity, visual coherence, and human-use logic. An autonomous evaluation agent applies these principles to identify scene issues, produce scores, and generate reports, enabling reliable, scene-specific judgments. Experiments demonstrate GREP’s high agreement with human preferences, its ability to improve scene quality through feedback, and insights into how future models might better balance planning and constraint adaptation.

By Mohan Cao, Yongsen Mao, Chucheng Xiang, Zhongyuan Liu, Zhihang Zhong, Haiping Wang, Yuan Liu

llms agents

arXiv AI

Aug 7

iARCS: Iterative Agentic RL for Controllable 3D Scene Generation

arXiv:2608. 06161v1 Announce Type: new Abstract: Synthetic 3D scene generation is increasingly used as a data source for computer vision and embodied AI, but existing generators often optimize perceptual realism without reliably satisfying task-critical functional constraints.

By Saugat Adhikari, Ashok Prasad Neupane, Pramish Paudel, Ajad Chhatkuli, Danda Pani Paudel

llms agents computer-vision reinforcement-learning robotics fine-tuning

arXiv Machine Learning

Oct 23

Building Presentation Intelligence for High-Quality Slide Generation

The paper introduces a unified training framework for automatic PowerPoint generation, combining cross‑validated data synthesis, rule‑based teacher enhancement, and a mixed‑teacher supervised fine‑tuning strategy. It further adds a reinforcement learning component with verifiable aesthetic metrics to refine slide visual attributes. Experiments show significant performance gains on PresentBench, outperforming existing models and improving aesthetic quality.

By Yuhang Xie, Cheng Li, Chenliang Li, Mingyu Xu, Mingwei Sun, Suhang Zheng, Ming Yan, Xiaoxiao Xu, Lin Qu

llms agents reinforcement-learning fine-tuning

Hugging Face Trending Papers

Jul 15

ThinkBLOX: 3D Indoor Scene Generation with Progressive Reasoning

While traditional graphics methods often synthesize 3D indoor scenes autoregressively or hierarchically, recent vision-language model (VLM)-based generators predominantly adopt a one-shot paradigm where the full layout is planned at once. This one-shot approach often requires global re-optimization or complete reconstruction during interactive editing (e.

llms reinforcement-learning fine-tuning multimodal safety

arXiv Computer Vision

Sep 1

FuncRoom-Agent: Sequential Feed-Forward 3D Functional Indoor Scene Generation

arXiv:2608.29519v1 Announce Type: new Abstract: We introduce Function-Room Generation, a new indoor 3D scene generation setting that creates rooms supporting explicit functional goals rather than mer...

By Hao Feng, Zhi Zuo, MingJian Liang, Jingyu Hu, Xiaowei Hu, Liupengfei Wu, Dian Zhang, Guoxin Fang, Zhengzhe Liu

agents reinforcement-learning benchmarks