Open-source initiative for open-ended realistic simulation of autonomous agents in physical and social worlds
Joined January 2026
- Tweets267
- Following521
- Followers1.1K
- Likes336
Pinned Tweet
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
SimWorld retweeted
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…
🧵👇
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!
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…
🧵👇
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/
SimWorld retweeted
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…
🧵👇
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
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!
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!
SimWorld retweeted
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…
SimWorld retweeted
MiniMax M3.1 Flash reshapes BuildingBench’s cost–quality frontier! Another open model making moves in 3D 🏗️🔥
🎈 73.3 overall, ranking #12.
🎈 Above SWE-2’s 67.3, taking its place on the Pareto frontier.
🎈 Close to the previous DeepSeek V4.1 Flash’s 72.9—and currently free through OpenRouter!
Its best reconstruction hits 88.8 on Melbourne’s Australian Centre for Contemporary Art.
How does it look alongside DeepSeek V4.1 Flash 1017 and #1 Opus 5.5? Comparison video below 👇
SimWorld retweeted
See DeepSeek’s 3D leap with your own eyes 👀🏗️
DeepSeek V4.1 Flash 1017 🆚 DS V4.1 Flash 🆚 GPT-6 Astra: three buildings, side by side.
The new open model improves on 11 of 12 buildings in BuildingBench, jumping from 72.9 → 81.9—closing in on Astra’s 84.3 at less than half the median cost ($3.01 vs $7.05/task).
Open models are getting seriously good at building worlds 🔥
Wow🙀🙀 DeepSeek V4.1 Flash 1017 joins BuildingBench’s top five—an exciting leap for open models!! 🔥
We tested its 3D building reconstruction from real photos. An open model delivering this level of spatial reasoning at this cost is exciting to see! 👀
🎈 81.9 overall, up from 72.9 for the previous version. A 9-point jump!
🎈 Slightly higher than Fable 5.1’s 81.4, and essentially level with Sonnet 5.5’s 82.1.
🎈 Estimated median cost: $3.01/task. About 1/11 of Fable 5.1’s cost and 1/15 of Sonnet 5.5’s.
DeepSeek V4.1 Flash 1017 is a big improvement over its last version🤯
Wow🙀🙀 DeepSeek V4.1 Flash 1017 joins BuildingBench’s top five—an exciting leap for open models!! 🔥
We tested its 3D building reconstruction from real photos. An open model delivering this level of spatial reasoning at this cost is exciting to see! 👀
🎈 81.9 overall, up from 72.9 for the previous version. A 9-point jump!
🎈 Slightly higher than Fable 5.1’s 81.4, and essentially level with Sonnet 5.5’s 82.1.
🎈 Estimated median cost: $3.01/task. About 1/11 of Fable 5.1’s cost and 1/15 of Sonnet 5.5’s.
SimWorld retweeted
🎉Excited to see two new US open models from this week:
📘Meta’s Muse Spark Open
📗NVIDIA’s Nemotron 3.5 Super VL
How well can they build in 3D? 🏗️👀
We tested both on BuildingBench: reconstructing real buildings from photographs.
📘Muse Spark Open (max): 56.9 at an estimated $8.59/task—comparable to Kimi K3’s 54.0.
📗 Nemotron 3.5 Super VL (max): 37.8 at an estimated $0.76/task—among the cheapest tested, with performance near GLM-5.3 Flash’s 33.0.
DeepSeek V4.1 Flash remains well ahead of both: 72.9 at an estimated $2.33/task. GLM-5.3 FlashX also scores higher, at 68.0.
Neither newcomer reaches the cost–quality frontier. More open models to choose from, and plenty of room to improve spatial reasoning!
Both ran in Claude Code at max effort. Costs are estimated median per task.
SimWorld retweeted
Watch how GPT‑6 Astra + WorldBox tackle MazeBench, from its first action to gem💎 #61—32,980 live actions and around 1B tokens.
Building bridges with boxes, launching across gaps, solving puzzles that span multiple rooms… all while the map fills in.
Remember, test, revise, repeat, and grab that gem. WorldBox offers the supporting layer for Astra.
🚨New level unlocked! 🚨 We doubled GPT‑6 Astra’s score on MazeBench with WorldBox, our agentic sandbox for spatial reasoning.
Astra: 23 gems 💎💎
Astra+WorldBox: 61 gems 💎💎💎💎💎
MazeBench, by @patience_cave, is a tough test of long-horizon spatial reasoning: 256 interconnected rooms where even Opus 5.5 used 2.2B tokens and collected just 13 of 100 gems.
WorldBox provides agents with an agentic sandbox, for managing long-term memory, inferring complex mechanics, and simulating reasoning.
Watch the sandbox take shape and the agent tackle increasingly tricky puzzles. 🧵
SimWorld retweeted
Long-horizon spatial reasoning remains a major challenge, even for the strongest frontier AI models.
Impressive results from @EnactraAI! 🚀 WorldBox boosts GPT-6 Astra from 23 to 61 gems on MazeBench, a 2.7× improvement!
Exciting to see how memory, world modeling, and simulation can help AI agents tackle much harder problems.
🚨New level unlocked! 🚨 We doubled GPT‑6 Astra’s score on MazeBench with WorldBox, our agentic sandbox for spatial reasoning.
Astra: 23 gems 💎💎
Astra+WorldBox: 61 gems 💎💎💎💎💎
MazeBench, by @patience_cave, is a tough test of long-horizon spatial reasoning: 256 interconnected rooms where even Opus 5.5 used 2.2B tokens and collected just 13 of 100 gems.
WorldBox provides agents with an agentic sandbox, for managing long-term memory, inferring complex mechanics, and simulating reasoning.
Watch the sandbox take shape and the agent tackle increasingly tricky puzzles. 🧵
SimWorld retweeted
Here’s what that progress looks like across the maze. 🗺️
Rooms visited by the end of each run:
🥉 Opus 5.5: 68
🥈 GPT‑6 Astra: 113
🥇 GPT‑6 Astra + WorldBox: 230 of 256
Brighter tiles mark more frequent visits. With WorldBox, the agent reaches almost 90% of the rooms and steps onto nearly twice as many distinct tiles as the Astra baseline.
WorldBox starts with empty memory and no skills. The agent writes its own notes and Python skills, reconstructs room geometry from camera views, and tests candidate moves in the sandbox.
Remembering where you’ve been helps make the next exploration decision.
What does that reasoning look like inside a difficult room? 👇
The model matters. So does the memory, context, and sandbox around it. Amazing results showing what the right combination can do!💯💯
🚨New level unlocked! 🚨 We doubled GPT‑6 Astra’s score on MazeBench with WorldBox, our agentic sandbox for spatial reasoning.
Astra: 23 gems 💎💎
Astra+WorldBox: 61 gems 💎💎💎💎💎
MazeBench, by @patience_cave, is a tough test of long-horizon spatial reasoning: 256 interconnected rooms where even Opus 5.5 used 2.2B tokens and collected just 13 of 100 gems.
WorldBox provides agents with an agentic sandbox, for managing long-term memory, inferring complex mechanics, and simulating reasoning.
Watch the sandbox take shape and the agent tackle increasingly tricky puzzles. 🧵
SimWorld retweeted
🚨New level unlocked! 🚨 We doubled GPT‑6 Astra’s score on MazeBench with WorldBox, our agentic sandbox for spatial reasoning.
Astra: 23 gems 💎💎
Astra+WorldBox: 61 gems 💎💎💎💎💎
MazeBench, by @patience_cave, is a tough test of long-horizon spatial reasoning: 256 interconnected rooms where even Opus 5.5 used 2.2B tokens and collected just 13 of 100 gems.
WorldBox provides agents with an agentic sandbox, for managing long-term memory, inferring complex mechanics, and simulating reasoning.
Watch the sandbox take shape and the agent tackle increasingly tricky puzzles. 🧵
SimWorld retweeted
RSI-Anything already passed 500 GitHub stars in just one day!
Thank you guys for the support!
Let's RSI Anything!
Excited to introduce RSI-Anything!
One RSI model that works across coding, GUI, planning, or even Science tasks.
Let's RSI Everything!
📄 Paper: arxiv.org/abs/2610.13912
💻 Code: github.com/Gen-Verse/RSI-Any…
#RSI #WorldModels #RSI #AIAgents #AIforScience #JEPA