HKUST Guangzhou and Tencent open-source VibeWorlding, an agent framework for building 3D worlds by chat
jiqizhixin · x · 2026-09-04
HKUST Guangzhou and Tencent AI Platform released VibeWorlding, a multimodal agent framework that builds interactive 3D worlds end-to-end via natural language — like vibe coding for 3D.
- Building 3D worlds still demands pro skills in asset retrieval, placement, collision avoidance, and rendering; existing agent frameworks are either rigid fixed pipelines or closed-source, with benchmarks too simple for real users' vague, contradictory requests
- VibeWorlding handles asset search, object placement, collision checking, and render verification through multi-turn dialogue, tool calls, and visual feedback — say "build a creepy desert temple" or "move that chair two meters forward"
- The team also open-sourced VWE-Bench, designed for realistic, messy user queries
- Claimed as the first fully open-source framework and benchmark for end-to-end 3D world construction
More from coding & agent
- GPT Sol plays real-time table tennis via latency-aware agent research loop — wzenus · 2026-10-21
- PostgreSQL 19 slips to November as LLM-assisted code review floods committers with edge cases — sanjaykalra · 2026-10-21
- 9x Vision open-sources video perception for agents: timestamped evidence via MCP and CLI — koto9x · 2026-10-21
- LangChain adds Human-in-the-Loop beta to Managed Deep Agents — LangChain · 2026-10-21
- Voxtral 3 ships a LiveKit-based voice agent SDK streaming listen-think-speak — MistralAI · 2026-10-21
- Open-sourced pixel art normals generator ships as Rust CLI and wasm library — HugoDuprez · 2026-10-20