VIENNA, Austria, June 5, 2026 /PRNewswire/ -- AGIBOT, a leading embodied AI company, hosted AGIBOT WORLD CHALLENGE 2026 alongside ICRA 2026 in Vienna, bringing together 526 research and enterprise teams from 27 countries to compete across two embodied AI tracks: Reasoning to Action and World Model. The competition highlighted a key shift in embodied AI evaluation, moving beyond simulation scores toward closed-loop testing on real robots, real tasks, and standardized benchmarks.
Participants tested and debugged robots in different tasks
Participants tested and debugged robots in different tasks
Team PrismBot received the championship award on stage
Final Results of the R2A Track
Group Photo of AGIBOT
Dual Tracks Focus on Reasoning to Action and World Modeling AGIBOT WORLD CHALLENGE 2026 featured two tracks designed around core capabilities in embodied AI. The Reasoning to Action (R2A) track evaluated how robots understand tasks, plan actions, and execute them in physical environments. The World Model (WM) track focused on how AI systems predict physical-world changes and model interactions based on robot actions and sensor inputs. Together, the two tracks reflected the broader evolution of embodied AI from task execution toward understanding, prediction, and decision-making.
This challenge drew research and industry teams from leading institutions and companies, including the Chinese Academy of Sciences, Tsinghua University, the University of Science and Technology of China, the University of California San Diego, Russia's Sber Robotics Center, Alibaba, Amap, and vivo. More than 100 teams surpassed the official baseline, reflecting strong participation from universities, research institutes, technology companies, startups, and individual developers across academia and industry.
The competition adopted a benchmark-driven format that combined online automated evaluation with an offline real-robot final in Vienna. Leveraging AGIBOT's EWMBench and Genie Sim Benchmark, the format enabled automated testing, standardized metrics, and reproducible results, offering a more consistent framework for evaluating embodied AI systems across simulation and real-world execution.
During the offline final, finalist teams completed tasks using the AGIBOT G2 humanoid robot in real-world scenarios. By incorporating real-robot validation into the evaluation process, the competition placed robot stability, physical-world adaptability, and long-horizon task reliability at the center of the scoring system, aligning technical evaluation more closely with practical deployment needs.
The Reasoning to Action (R2A) track, upgraded from the 2025 Manipulation track, expanded the evaluation from action execution to the full process of environment understanding, task planning, and physical execution. Teams trained reasoning-and-manipulation models using the AGIBOT WORLD open-source dataset and evaluated them through Genie Sim 3.0, with the benchmark covering language understanding, spatial reasoning, atomic skills, disturbance adaptation, and zero-shot transfer. In the final ranking, PrismBot from vivo won the championship, followed by Shanghai RoboParty's RP-VLA and GreenVLA.
Alongside the competition, AGIBOT and Dexmal launched a real-supermarket benchmark track focused on end-to-end decision-making and whole-body control. Set in a highly realistic retail environment, the track required models to complete the full mobile manipulation process, from autonomous navigation and item picking to item transport and placement, under real physical constraints such as shelf height limits and randomized item placement. Through API-based remote control, participants' algorithms directly controlled real robots, creating a practical benchmark for evaluating embodied intelligence in deployment-oriented scenarios.
In the World Model (WM) track, NeoVerse-ABot, a joint team from the Institute of Automation of the Chinese Academy of Sciences, and Amap CV Lab, won first place. The PAI@IAII team from the Institute of Industrial Artificial Intelligence, Chinese Academy of Sciences, ranked second, while the Loop team from the University of Science and Technology of China placed third. This track incorporated non-ideal physical interactions, including object drops and grasping failures, to better reflect the complexity of real-world interaction and provide a more practical evaluation framework for world model research.
Full-Stack Toolchain Supports Standardized Real-Robot Validation Beyond the competition itself, AGIBOT opened a full-stack toolchain covering real-world data, simulation evaluation, and real-robot testing. The toolchain included the AGIBOT WORLD open-source dataset, Genie Sim 3.0, and the AGIBOT G2 robot platform, helping developers validate models across the path from training to simulation and physical deployment.
By combining dual-track evaluation, automated benchmarking, and real-robot testing, AGIBOT WORLD CHALLENGE 2026 contributed to a more practical and reproducible evaluation framework for embodied AI. EWMBench and Genie Sim Benchmark supported standardized metrics, automated evaluation, and comparable results across simulation and physical testing, addressing common challenges such as inconsistent evaluation criteria and the gap between simulated performance and real-world deployment.
The competition also moved beyond a narrow focus on simulation scores by placing real-robot stability, physical consistency, and long-horizon task reliability at the center of evaluation. This approach encouraged teams to develop models not only for benchmark performance, but also for deployability, generalization, and robustness in real-world environments.
The technical and ecosystem resources developed through the competition will be integrated into AGIBOT's ongoing benchmark development and open-source ecosystem. Moving forward, AGIBOT plans to launch an online simulation leaderboard, introduce more test tasks and diversified benchmarks, and support more comprehensive quantitative evaluation of model capabilities. The company will also continue to refine its benchmarks and full-stack toolchain, working with global research institutions, developers, and industry partners to help embodied intelligence progress from individual algorithmic advances toward systems that can be deployed and scaled in real-world settings.
About AGIBOT AGIBOT is an Embodied AI foundation model company developing both the intelligence layer and the corresponding robotic embodiments needed to bring general intelligence into the physical world. AGIBOT's "Three Intelligences in One" architecture integrates Locomotion Intelligence, Interaction Intelligence, and Manipulation Intelligence into a unified embodied system. Its portfolio spans humanoid robots, quadrupeds, dexterous systems, and commercial cleaning solutions. In March 2026, AGIBOT announced that its 10,000th robot had rolled off the production line.
Artikel teilen