1
Roblox launches an AI-powered game-creation feature in its mobile app
Roblox移动端上线AI游戏创作功能，同时停用视频通话，转向单线索生成3D场景的新模型
Roblox's new "Build" feature lets users generate basic games using a single text prompt.
2
Authoring for Living Worlds: Tool-Constrained LLM Agents for Executable Multi-Actor Scenarios
AI代理自动生成3D游戏可执行的叙事场景，让非专业人士也能创作动态多角色视频。
arXiv:2604.10383v2 Announce Type: replace Abstract: We use LLM agents to author executable specifications for a living world: formal Graphs of Events …
3
高德发布通用世界模型工坊ABot-World Studio：5090单卡可生成小时级实时交互式视频与3D场景
高德最新世界模型工坊可单卡生成小时级实时交互视频与3D场景，首创“时空任意门”实现全尺度空间无缝穿梭。
4
SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion
场景级3D扩散新思路，自举合成城市规模三维数据，生成质量与扩展性兼顾。
arXiv:2607.05392v1 Announce Type: new Abstract: We present SynCity 3000, a framework for generating 3D scenes that are globally coherent while enablin…
5
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
一句话指挥AI生成复杂斜顶与弧形室内场景，突破传统直角空间限制，3D设计效率倍增。
arXiv:2607.02407v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in 3D indoor synthesis for Manh…
6
SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation
多智能体协作打造动态3D场景，AI内容生成迎来新范式
arXiv:2607.01766v1 Announce Type: new Abstract: LLM agents are increasingly used to translate natural language into 3D scenes in a procedural way, but…
7
TrafficAlign: Aligning Large Language Models for Traffic Scenario Generation
用大模型对齐技术生成逼真交通场景，自动驾驶仿真数据难题迎来新解法。
arXiv:2606.29097v1 Announce Type: new Abstract: Recent research has investigated the use of large language models (LLMs) to generate traffic scenarios…
8
IMAGIN-4D: Image-Guided Controllable Interaction Generation
图像引导的4D交互生成新方法，让AI根据单张图片自动生成可控的动态场景。
arXiv:2606.23675v1 Announce Type: new Abstract: Generating human-object interactions (HOI) is central to character animation, robotics, AR/VR, and emb…
9
HDSL: A Hierarchical Domain-Specific Language for Structured 3D Indoor Scene Generation and Localized Editing with LLM Agents
用层次化领域特定语言融合LLM智能体，实现结构化3D室内场景一键生成与精准局部编辑。
arXiv:2606.09738v1 Announce Type: new Abstract: Text-driven indoor scene generation and editing require an intermediate representation that language m…
10
VESTA: A Fully Automated Scenario Generation and Safety Evaluation Framework for LLM Agents
全自动生成测试场景，破解LLM Agent安全评估的痛点，附18页详实方法论与图表。
arXiv:2606.08531v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evolving from simple text-based interaction systems into…
11
Claude Code-Driving Scenario Mining for the Argoverse 2 Challenge
用Claude Code挖掘复杂驾驶场景，Argoverse 2挑战赛的新解法
arXiv:2606.09180v1 Announce Type: new Abstract: We present our submission to the CVPR 2026 Argoverse 2 Scenario Mining Challenge. Our system uses a fo…
12
高德发布ABot-Earth0.5：跨越2D蒸馏模式，以3D原生驱动高一致性场景生成
ABot-Earth0.5正式开放内测
13
EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents
LLM智能体自我改进生成安全关键驾驶场景，实现帕累托最优进化。
arXiv:2606.03678v1 Announce Type: new Abstract: Generating safety-critical scenarios is essential for validating and improving autonomous driving syst…
14
V2XCrafter: Learning to Generate Driving Scene Across Agents
ACL论文提出V2XCrafter，用扩散模型生成多智能体驾驶场景，缓解V2X数据集稀缺问题，推动协作感知泛化。
arXiv:2605.29471v1 Announce Type: new Abstract: Collaborative driving systems leverage vehicle-to-everything (V2X) communication for multi-agent colla…