SimWorld (@simworld_ai) header
SimWorld (@simworld_ai) profile picture

Open-source initiative for open-ended realistic simulation of autonomous agents in physical and social worlds

Joined January 2026
Photo by SimWorld (@simworld_ai)Photo by SimWorld (@simworld_ai)Photo by SimWorld (@simworld_ai)Photo by SimWorld (@simworld_ai)Photo by SimWorld (@simworld_ai)Photo by SimWorld (@simworld_ai)Photo by SimWorld (@simworld_ai)Photo by SimWorld (@simworld_ai)Photo by SimWorld (@simworld_ai)Photo by SimWorld (@simworld_ai)
Gemini 4 Hydrogen builds scenes faster than Carbon and Argon—even while taking nearly twice as many actions. ~45 minutes per scene, versus Carbon’s 76 and Argon’s 70. Its trick: run build scripts in the background and check back instead of waiting for each step to finish.
4
3
1
7
531
SimWorld retweeted
Astra tops BuildingBench, but Sol comes surprisingly close for a lot less money.
3
1
14
889
SimWorld retweeted
Qwen4 Max on BuildingBench 🏛️ Photos in, a usable 3D model out. #Qwen #AI #3D #Architecture
3
3
17
1,183
Amazing music
Enactra Agentic Simulation 🤖🎬 Robots you can control, in worlds you can direct. Every frame comes annotated. 🔊 Sound on #AgenticSimulation #Robotics #EmbodiedAI
1
3
308
SimWorld retweeted
Enactra Agentic Simulation 🤖🎬 Robots you can control, in worlds you can direct. Every frame comes annotated. 🔊 Sound on #AgenticSimulation #Robotics #EmbodiedAI
24
34
8
148
27,398
SimWorld retweeted
World simulation with both physical & visual fidelity will be playing a key role in physical AI
Enactra Agentic Simulation 🤖🎬 Robots you can control, in worlds you can direct. Every frame comes annotated. 🔊 Sound on #AgenticSimulation #Robotics #EmbodiedAI
3
3
15
1,085
SimWorld retweeted
I've watched this video more than 50 times, always with the sound on. The cinematic quality still impresses me. I highly recommend experiencing it with audio. 🔊
Enactra Agentic Simulation 🤖🎬 Robots you can control, in worlds you can direct. Every frame comes annotated. 🔊 Sound on #AgenticSimulation #Robotics #EmbodiedAI
1
3
19
2,369
This is a massive game-changer for Embodied AI! Having a highly controllable simulation where "every frame comes annotated" out-of-the-box is going to save researchers countless hours of data processing. The visual fidelity is absolutely incredible too.! #EmbodiedAI #Robotics
Enactra Agentic Simulation 🤖🎬 Robots you can control, in worlds you can direct. Every frame comes annotated. 🔊 Sound on #AgenticSimulation #Robotics #EmbodiedAI
12
18
110
17,250
𝗚𝗲𝗺𝗶𝗻𝗶 𝟰 𝗖𝗮𝗿𝗯𝗼𝗻 gets within 1.9 points of Fable 5.2 on Code4Scene—at ~1/10 the cost. 🥈 #2 in physical validity 🛠️ 95 tool calls vs. Fable’s 238 📈 +4.7 points over Argon for just $0.21 more per scene
1
2
5
383
🥇 𝗖𝗹𝗮𝘂𝗱𝗲 𝗙𝗮𝗯𝗹𝗲 𝟱.𝟮 𝗷𝘂𝘀𝘁 𝘁𝗼𝗼𝗸 #𝟭 𝗼𝗻 𝗖𝗼𝗱𝗲𝟰𝗦𝗰𝗲𝗻𝗲. It also found a loophole in our collision checker. 👀 We tested it on 20 tasks building 3D scenes with code. It scored 𝟴𝟰.𝟰/𝟭𝟬𝟬, ahead of Sonnet 5.5 and Opus 5.5. What stood out: 𝟭. 𝗜𝘁 𝗴𝗮𝗺𝗲𝗱 𝘁𝗵𝗲 𝗰𝗵𝗲𝗰𝗸𝗲𝗿. It merged buildings into single objects so internal overlaps stopped registering as collisions. The overlaps remained; the checker stopped seeing them. We didn’t observe this in Sonnet 5.5 or Opus 5.5. 𝟮. 𝗕𝗶𝗴𝗴𝗲𝗿 𝘄𝗼𝗿𝗹𝗱𝘀. 𝗠𝗲𝘀𝘀𝗶𝗲𝗿 𝗴𝗲𝗼𝗺𝗲𝘁𝗿𝘆. ~1,650 objects per scene vs. 784 for Fable 5.1. Prompt alignment jumped #8 → #1, while physical validity fell #1 → #7. 𝟯. 𝗜𝘁𝘀 𝗲𝗱𝗴𝗲 𝗶𝘀 𝗰𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝗰𝘆. Typical scene scores are comparable to Sonnet and Opus. But its worst scene scored 73.7—the highest minimum of any model we tested. 𝟰. 𝗔 𝗹𝗼𝘁 𝗼𝗳 𝘁𝗵𝗶𝗻𝗸𝗶𝗻𝗴. 𝗔 𝗹𝗼𝘁 𝗼𝗳 𝗰𝗵𝗲𝗰𝗸𝗶𝗻𝗴. ~74 scene views and ~560k output tokens per build, mostly thinking. Opus 5.5 used 42 views and 298k tokens. Explore the leaderboard and see what the agents built 👇 simworld-ai-code4scene.stati…
4
2
11
1,515
Can reinforcement learning solve inverse kinematics precisely? Introducing 𝗣𝗼𝗹𝗶𝗰𝘆𝗜𝗞 🦾, a goal-conditioned RL policy for high-precision inverse kinematics. On a real arm, it reaches median errors of 𝟬.𝟱𝟬 𝗺𝗺 𝗮𝗻𝗱 𝟬.𝟭𝟮° and holds the goal pose on 𝟮.𝟱× 𝗺𝗼𝗿𝗲 𝘁𝗮𝘀𝗸𝘀 than the best classic IK controller. 🌐 tinaliu0123.github.io/Policy… 🧵👇
15
57
10
509
53,402
SimWorld retweeted
"No OCR, read text natively from images" continues! We showed this with deep research agents: it not only improves performance but also reduces tool calls! Post-training to work with page images gives a big boost - likely because these open-weight models haven't been trained to work with page images yet? Exciting work led by @Hughie_Hu43 !
(1/7) 🚀 Introducing DR Pixel, the first open-source deep research agent that searches and reasons directly over page images, no OCR. On 1.06M pages, our trained 27B model matches GPT-5.4. 📄 arxiv.org/abs/2611.03097 Joint work from @BerkeleyNLP, @rtnldynamics!
7
26
2
248
17,949
SimWorld retweeted
Check out SceneBloom! Diffusion-powered, agentic 3D indoor generation for embodied learning.
Can generated scenes train embodied agents better than real-world data? Introducing 𝗦𝗰𝗲𝗻𝗲𝗕𝗹𝗼𝗼𝗺 🌸, an agentic framework that generates realistic, diverse, simulation-ready 3D scenes for embodied learning. 🤖 𝗕𝗲𝘁𝘁𝗲𝗿 𝘁𝗿𝗮𝗶𝗻𝗶𝗻𝗴 𝗱𝗮𝘁𝗮: 1.7× the navigation gain of an equal number of real scans ✅ 𝗣𝗵𝘆𝘀𝗶𝗰𝗮𝗹𝗹𝘆 𝗽𝗹𝗮𝘂𝘀𝗶𝗯𝗹𝗲: no detected mesh collisions, and the most physically stable 🏠 𝗥𝗲𝗮𝗹𝗶𝘀𝘁𝗶𝗰: layouts closest to real rooms 📄 arxiv.org/abs/2610.32978 💻 github.com/Tinaliu0123/scene… 🌐 tinaliu0123.github.io/sceneb… 🧵👇
2
6
37
2,342
SimWorld retweeted
RT-SAFE: Are the Newer Agents Safer in REAL TIME Environment? 👀 REASONING LATENCY matters — the world keeps moving during inference. ⚡ DeepSeek V4 Flash Vision → V4.1 Flash: 50% lower response time; safety events 27.6 → 20.4 (−26%). 🧭 Gemini 3.8 Flash → 4 Argon: 30% lower response time, 18% fewer decisions; safety events 16.0 → 10.4 (−35%). 💭 Kimi K3 → K3.1 Pro: 33% fewer decisions; safety events 36.0 → 28.0 (−22%). Responses still averaged ~42 s. 🤖 GPT-5.6 Sol → 6.1 Sol: 11% fewer decisions, but safety events 13.2 → 16.0 (+21%). ⚠️ SAFETY FAILURES PERSIST. Faster or more efficient doesn’t automatically mean safer. More model examples & failure analyses coming soon! 💻 Code: github.com/XTRose29/RT-SAFE 📄 Paper: arxiv.org/abs/2610.09294 🌐 Website: xtrose29.github.io/RT-SAFE/
3
1
14
1,407
Can generated scenes train embodied agents better than real-world data? Introducing 𝗦𝗰𝗲𝗻𝗲𝗕𝗹𝗼𝗼𝗺 🌸, an agentic framework that generates realistic, diverse, simulation-ready 3D scenes for embodied learning. 🤖 𝗕𝗲𝘁𝘁𝗲𝗿 𝘁𝗿𝗮𝗶𝗻𝗶𝗻𝗴 𝗱𝗮𝘁𝗮: 1.7× the navigation gain of an equal number of real scans ✅ 𝗣𝗵𝘆𝘀𝗶𝗰𝗮𝗹𝗹𝘆 𝗽𝗹𝗮𝘂𝘀𝗶𝗯𝗹𝗲: no detected mesh collisions, and the most physically stable 🏠 𝗥𝗲𝗮𝗹𝗶𝘀𝘁𝗶𝗰: layouts closest to real rooms 📄 arxiv.org/abs/2610.32978 💻 github.com/Tinaliu0123/scene… 🌐 tinaliu0123.github.io/sceneb… 🧵👇
2
9
1
60
5,788
The AI-generated indoor environments are impressively realistic, with physically plausible structures and coherent spatial layouts.
🔥Synthetic 3D worlds can beat real-world scans! Introducing SceneBloom: diffusion-powered, agentic 3D indoor generation for training embodied AI. Realistic. Diverse. Physically valid. Executable. → Better 3D worlds → Better embodied agents. 1.7× navigation gain vs. equal real scans Zero detected mesh collisions 37.45% → 4.25% contract violations
1
7
503
SimWorld retweeted
🔥Synthetic 3D worlds can beat real-world scans! Introducing SceneBloom: diffusion-powered, agentic 3D indoor generation for training embodied AI. Realistic. Diverse. Physically valid. Executable. → Better 3D worlds → Better embodied agents. 1.7× navigation gain vs. equal real scans Zero detected mesh collisions 37.45% → 4.25% contract violations
8
14
1
101
6,480
SimWorld retweeted
I’m so glad to see open-source coding agents really catching up in 3D coding!
Wow! Kimi K3.1 Pro leaps into BuildingBench’s top six! Another open model making serious strides in 3D 🏗️🔥 🎈54.0 → 81.6 from Kimi K3—a massive 27.6-point jump! 🎈Essentially matches DeepSeek V4.1 Flash 1017’s 81.9, joining the cluster around Sonnet 5.5 and Fable 5.1. 🎈Estimated median cost: $12.58/task. Cheaper than Sonnet and Fable, though DeepSeek remains more cost-efficient at $3.01. The reconstruction shown here scores 90.8: Melbourne’s Australian Centre for Contemporary Art, rebuilt from photographs. Exciting to see more open models reaching this level of spatial reasonin!
1
3
30
1,589
SimWorld retweeted
Wow! Kimi K3.1 Pro leaps into BuildingBench’s top six! Another open model making serious strides in 3D 🏗️🔥 🎈54.0 → 81.6 from Kimi K3—a massive 27.6-point jump! 🎈Essentially matches DeepSeek V4.1 Flash 1017’s 81.9, joining the cluster around Sonnet 5.5 and Fable 5.1. 🎈Estimated median cost: $12.58/task. Cheaper than Sonnet and Fable, though DeepSeek remains more cost-efficient at $3.01. The reconstruction shown here scores 90.8: Melbourne’s Australian Centre for Contemporary Art, rebuilt from photographs. Exciting to see more open models reaching this level of spatial reasonin!
10
7
2
44
4,878
Thanks AK @_akhaliq for featuring our work! Excited to share OpenVLHarness, a multimodal agent that inspect, compute, and reason over evidence. The technical core: • A capability layer gives consistent interfaces for various tools such as perception and search, and renders their outputs into observations the model can inspect. • Persistent multimodal memory retains images, masks, numerical arrays, and web references under reusable handles. • A coding agent computes over those artifacts to combine evidence across tools. Across 22 benchmarks and 8 backbones, we see average gains of 9.7–12.6 points over matched no-tool baselines. Evidence acquisition and additional reasoning are complementary! A joy collaborating with this UCLA × Apple team. Huge shoutout to @yu_bryan_zhou, @cfyang58, @RuiSun94013021, @DiWu0162 , Sibo Peng, Mingyang Zhang, Zhen Yang, Ruiyi Zhang, @zhegan4 and @kaiwei_chang! 🎉
OpenVLHarness Real World Visual Agentic Tool-Use with Multimodal Memory paper: huggingface.co/papers/2610.2…
4
8
38
3,055