Plurai raises $13 million to simulate and tune AI agents
The seed round, led by Team8, funds digital twins that post-train small open-weight models for customer workflows.
Stories per day · 30 days
5 RSS
Relatedrobotics20benchmark4benchmarks4nvidia4embodied-ai3gemini3reinforcement-learning3sim-to-real3world-models3allenai2climate2dexterous-manipulation2genie-42google-deepmind2gpu2huggingface2isaac-lab2libero2
70 stories, newest first · one card per story
Stories tagged #simulation
NVIDIA introduces GR00T 2 robot world action model at CoRL
NVIDIA says GR00T 2 hit 71% average success across 50 tasks with one demonstration and 95% with five.
DexForesight lifts dexterous policies with implicit spatial foresight
On 11 DexJoCo tasks success rises from 49.4% to 60.5%; three real-robot tasks reach 58.3% versus 50.0%.
PhysOPSD uses executable code as privilege for video generation
Authors say the method beats supervised fine-tuning and reinforcement learning with 3,000 samples while keeping general video quality.
RoboScript learns manipulation tasks in context from one demonstration
Authors report 83.4% mean success on all 50 RoboTwin 2.0 tasks without gradient updates, over 20 points above the strongest trained policy.
.gif&w=828&q=75)
War game reveals solar geoengineering arms race risks
War game reveals geopolitical tensions and disinformation risks in international responses to solar geoengineering technologies.
1
ToyBlocks is a controlled world for robot learning
Hugging Face published an Allen Institute for AI post; the available item gives only the project title.
Physicl raises $10M to simulate realistic worlds for robots
Physicl repurposes its 3D rendering tech to generate high-fidelity simulations for training physical AI models.
PyRUA-DataFarm automates robot data collection
PyRUA-DataFarm cuts robot data costs to $21 per task using an LLM agent in simulation.
Kierston simulation for crime investigation
KierstonBench benchmark tests language models on 125,000-resident Allentown simulation for record linkage and investigation tasks.
Column says phishing drills still test yesterday's lures
The author urges measuring reporting speed and response, not only click rates, as AI-written lures improve.
arXiv releases AgenticMobility platform for AI mobility agents
AgenticMobility is an open-source platform studying how AI agents interact in urban transportation simulations over repeated experience.
Cyber-to-physical framework assesses water system security
Machine learning model predicts physical impacts from cyber compromises in water networks using hydraulic simulations.
Gym-Anything builds RoboWorld, 25 coding-agent robotics simulations
Frontier models score an average reward of 0.06 and fail every RoboWorld test task; several teaching methods raise performance.
Simantic launches a firmware simulator for AI agents
The Rust simulator targets selected STM32, ESP32, and RP2040 boards so agents can test firmware without flashing hardware.
6
DeepMind announces Genie 4 real-time world model with native audio
A research preview goes to trusted testers first, then Google AI Ultra subscribers in Project Genie and early Gemini API partners.
1
SO-101 Bench benchmarks language-conditioned spatial robot manipulation
A simulated twin matched the real arm's policy ranking exactly, though simulation overestimated success.
LongChang tests whether LLMs can discover altered physical laws
Among 12 models, only GPT-6-Astra discovered laws, at a reported rate of 16.7 percent.
Sim-trained ZAP robot policy hits 96.7% on real tasks
A 27B vision-language model fine-tuned only in simulation matches GPT-6 Astra and beats MolmoAct2's 33.3% in the same harness.
PhysEvolve trains VLMs on executable worlds for physical reasoning
From Qwen3-VL-8B-Instruct, the paper reports PhysBench Throwing up 8.8 and ContPhy Goal-Pit up 24.4 points.
The Trinity evolves multimodal-agent harnesses from shared capabilities
The authors report mean gains of 34 points on 28 training benchmarks and 26 points on 18 unseen benchmarks.
SceneBloom generates collision-free indoor layouts for embodied agent training
Navigation policies trained on its scenes beat policies trained on the same number of real scans in held-out scans.
Microduck trains in simulation and deploys with Isaac Lab 3.0
No post body was available, so only the sim-to-real Microduck and Isaac Lab 3.0 topic is known.
NVIDIA announces open SimReady Central library for robotics and AI factories
The post gives no asset count, license terms, or release date beyond the announcement itself.