←
SimWorld277 posts
SimWorld avatar

SimWorld

@simworld_ai

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

◷ Joined January 2026▧ 42 Photos and videos
SimWorld avatar
SimWorld@simworld_ai·Nov 14

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.

0:30
Enactra AI avatar
⟳ SimWorld retweeted
Enactra AI@EnactraAI·Nov 18

Astra tops BuildingBench, but Sol comes surprisingly close for a lot less money.

Zhiting Hu avatar
⟳ SimWorld retweeted
Zhiting Hu@ZhitingHu·Nov 16

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

1:23
Lianhui Qin avatar
⟳ SimWorld retweeted
Lianhui Qin@Lianhuiq·Nov 16

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

1:23
Yingcheng Charles Wu avatar
⟳ SimWorld retweeted
Yingcheng Charles Wu@Charles_Y_Wu·Nov 16

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

1:23
SimWorld avatar
SimWorld@simworld_ai·Nov 12

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

0:24
SimWorld avatar
SimWorld@simworld_ai·Nov 12

🥇 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…

0:25
Yuhan (Tina) Liu avatar
⟳ SimWorld retweeted
Yuhan (Tina) Liu@l_yuhan7272·Nov 5

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… 🧵👇

1:30
Sewon Min avatar
⟳ SimWorld retweeted
Sewon Min@sewon__min·Nov 3

"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!

0:47
Lianhui Qin avatar
⟳ SimWorld retweeted
Lianhui Qin@Lianhuiq·Oct 29

Check out SceneBloom! Diffusion-powered, agentic 3D indoor generation for embodied learning.

Post attachment

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… 🧵👇

0:38
Rose Xu avatar
⟳ SimWorld retweeted
Rose Xu@XTRose88·Oct 29

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/

1:00
Yuhan (Tina) Liu avatar
⟳ SimWorld retweeted
Yuhan (Tina) Liu@l_yuhan7272·Oct 28

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… 🧵👇

0:38
SimWorld avatar
SimWorld@simworld_ai·Oct 28

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

0:38