For our teams, this evolution raises very practical questions. How can we produce 3D content faster? How can we more easily adapt it to a wide range of devices? How can we use artificial intelligence judiciously? Which tasks should we delegate to it, and which ones are better kept in-house? And above all, how will these new tools transform the work of 3D professionals?<\/p>\n\n\n\n
A specific need for XR applications<\/h2>\n\n\n\n![\"\"](\"https:\/\/www.immersion.fr\/wp-content\/uploads\/2026\/10\/DSC02058-1024x683.jpg\")
<\/figure>\nAs a partner in the European research project MOSAICO<\/a>, Immersion develops among other things 3D<\/a> and extended reality (XR) applications and experiences. This expertise entails specific constraints: models must be adapted to the hardware used, available computing power, and the performance requirements of each headset or XR environment. These constraints also apply to the applications themselves, particularly regarding resource and energy consumption. With the advent of artificial intelligence, Immersion a European expert in immersive and collaborative technologies<\/a> is exploring the most effective process for the considered integration of AI into its value chain. This is one of the key objectives of the MOSAICO project. <\/p>\n\n\n\nIn this context, practical experience shows that relying on a single general-purpose AI tool does not necessarily meet a developer’s needs. Producing 3D content may require a range of skills and, consequently, multiple complementary agents. <\/p>\n\n\n\n
The use case studied in MOSAICO therefore draws on several specialized models. Trellis can be used to generate 3D models, iMotion for 3D animation, and UniRig to automate character rigging the process of creating the internal structure that enables animation. The goal is to have these various components work together within an architecture capable of orchestrating the different stages. <\/p>\n\n\n\n
A multi-agent approach makes it possible to distribute tasks among several specialized agents, rather than requiring a single model to handle the entire process.<\/p>\n<\/div><\/div>\n\n\n\n
Moving from using software to describing an expected result<\/h2>\n\n\n\n\nThis shift primarily changes the way work is approached. <\/p>\n\n\n\n
In a traditional workflow, the professional performs the various tasks directly within their 3D creation software. They know which tools to use and execute the steps themselves to achieve the desired result. <\/p>\n\n\n\n
With multiple specialized agents, some of these operations can be defined upfront. The professional describes the intended outcome, and the agents then handle specific steps using the necessary tools iteratively and can revert to the user when information or a decision is required. <\/p>\n\n\n\n
Early experiments with the Model Context Protocol (MCP) illustrate this evolution. This protocol enables an AI model to interact with external tools and resources. <\/p>\n\n\n\n
In a 3D creation environment, this opens up the possibility for the AI \u200b\u200bto communicate with software and tools installed on the machine and to execute specific operations. In a 3D creation scenario, for instance, the professional could describe the expected result rather than manually performing every step of modeling a vehicle. The various necessary tools would then be engaged to handle parts of the creation process. <\/p>\n\n\n\n
The change, therefore, lies not only in the tool being used but also in how the professional defines the objective and interacts with their work environment.<\/p>\n<\/div>![\"\"](\"https:\/\/www.immersion.fr\/wp-content\/uploads\/2026\/10\/Mosaico_BEM_VR-3-1-scaled.jpg\")
<\/figure><\/div>\n\n\n\nSpecialized agents to meet the demands of XR<\/h2>\n\n\n\n![\"\"](\"https:\/\/www.immersion.fr\/wp-content\/uploads\/2026\/10\/I03A0242-retouchee-scaled.jpg\")
<\/figure>\nCreating a 3D model or environment is only part of the challenge. In XR applications, the resulting 3D content must then run on specific hardware. <\/p>\n\n\n\n
However, headsets do not all share the same hardware and graphics capabilities. Factors such as the number of displayable polygons, texture resolution, scene complexity, and expected performance levels vary significantly from one device to another. Adapting content to these varying constraints still relies, to some extent, on repetitive manual intervention. <\/p>\n\n\n\n
Beyond optimizing visual performance, this work also aims to improve application energy efficiency. The limited battery life of headsets poses a significant obstacle to certain professional use cases. A key objective is therefore to reduce application energy consumption, thereby extending the operating time of battery-powered devices and facilitating their integration into prolonged operational workflows. <\/p>\n\n\n\n
Specialized agents could intervene earlier in the process. They could identify the target hardware’s specifications, analyze the generated content, and either propose or implement the necessary optimizations. <\/p>\n\n\n\n
For Immersion, this aspect is of strategic importance. One of the goals of the Mosa\u00efco use case is to explore how these various agents can help produce 3D content more efficiently while accounting for the performance constraints of XR hardware.<\/p>\n<\/div><\/div>\n\n\n\n
Save time without eliminating human oversight<\/h2>\n\n\n\n\nThe primary, tangible benefit of these new workflows enhanced by agentic AI is the reduction of time spent on repetitive tasks and various preparation stages. <\/p>\n\n\n\n
Currently, a single piece of content may require multiple adaptations for use across different devices. Part of the work involves identifying the specific constraints of each platform and making the necessary adjustments. <\/p>\n\n\n\n
If this knowledge could be integrated into the process, certain operations could be performed more systematically. Work completed once could also serve as a foundation for future adaptations, guided by checks and rules tailored to specific needs. <\/p>\n\n\n\n
However, the goal is not merely faster execution; process reliability is also a key factor. Automating certain operations and using specialized agents for verification could minimize redundancy and ensure greater consistency across projects. <\/p>\n\n\n\n
Nevertheless, this approach requires maintaining human oversight. The professional remains responsible for the final outcome and must be able to understand the system’s output, the rationale behind specific operations, and any corrections that may be required.<\/p>\n<\/div>![\"\"](\"https:\/\/www.immersion.fr\/wp-content\/uploads\/2026\/10\/Mosaico_BEM_Normal-1-scaled.jpg\")
<\/figure><\/div>\n\n\n\nA new place for 3D expertise<\/h2>\n\n\n\n
<\/figure>As a partner in the European research project MOSAICO<\/a>, Immersion develops among other things 3D<\/a> and extended reality (XR) applications and experiences. This expertise entails specific constraints: models must be adapted to the hardware used, available computing power, and the performance requirements of each headset or XR environment. These constraints also apply to the applications themselves, particularly regarding resource and energy consumption. With the advent of artificial intelligence, Immersion a European expert in immersive and collaborative technologies<\/a> is exploring the most effective process for the considered integration of AI into its value chain. This is one of the key objectives of the MOSAICO project. <\/p>\n\n\n\n In this context, practical experience shows that relying on a single general-purpose AI tool does not necessarily meet a developer’s needs. Producing 3D content may require a range of skills and, consequently, multiple complementary agents. <\/p>\n\n\n\n The use case studied in MOSAICO therefore draws on several specialized models. Trellis can be used to generate 3D models, iMotion for 3D animation, and UniRig to automate character rigging the process of creating the internal structure that enables animation. The goal is to have these various components work together within an architecture capable of orchestrating the different stages. <\/p>\n\n\n\n A multi-agent approach makes it possible to distribute tasks among several specialized agents, rather than requiring a single model to handle the entire process.<\/p>\n<\/div><\/div>\n\n\n\n This shift primarily changes the way work is approached. <\/p>\n\n\n\n In a traditional workflow, the professional performs the various tasks directly within their 3D creation software. They know which tools to use and execute the steps themselves to achieve the desired result. <\/p>\n\n\n\n With multiple specialized agents, some of these operations can be defined upfront. The professional describes the intended outcome, and the agents then handle specific steps using the necessary tools iteratively and can revert to the user when information or a decision is required. <\/p>\n\n\n\n Early experiments with the Model Context Protocol (MCP) illustrate this evolution. This protocol enables an AI model to interact with external tools and resources. <\/p>\n\n\n\n In a 3D creation environment, this opens up the possibility for the AI \u200b\u200bto communicate with software and tools installed on the machine and to execute specific operations. In a 3D creation scenario, for instance, the professional could describe the expected result rather than manually performing every step of modeling a vehicle. The various necessary tools would then be engaged to handle parts of the creation process. <\/p>\n\n\n\n The change, therefore, lies not only in the tool being used but also in how the professional defines the objective and interacts with their work environment.<\/p>\n<\/div> Creating a 3D model or environment is only part of the challenge. In XR applications, the resulting 3D content must then run on specific hardware. <\/p>\n\n\n\n However, headsets do not all share the same hardware and graphics capabilities. Factors such as the number of displayable polygons, texture resolution, scene complexity, and expected performance levels vary significantly from one device to another. Adapting content to these varying constraints still relies, to some extent, on repetitive manual intervention. <\/p>\n\n\n\n Beyond optimizing visual performance, this work also aims to improve application energy efficiency. The limited battery life of headsets poses a significant obstacle to certain professional use cases. A key objective is therefore to reduce application energy consumption, thereby extending the operating time of battery-powered devices and facilitating their integration into prolonged operational workflows. <\/p>\n\n\n\n Specialized agents could intervene earlier in the process. They could identify the target hardware’s specifications, analyze the generated content, and either propose or implement the necessary optimizations. <\/p>\n\n\n\n For Immersion, this aspect is of strategic importance. One of the goals of the Mosa\u00efco use case is to explore how these various agents can help produce 3D content more efficiently while accounting for the performance constraints of XR hardware.<\/p>\n<\/div><\/div>\n\n\n\n The primary, tangible benefit of these new workflows enhanced by agentic AI is the reduction of time spent on repetitive tasks and various preparation stages. <\/p>\n\n\n\n Currently, a single piece of content may require multiple adaptations for use across different devices. Part of the work involves identifying the specific constraints of each platform and making the necessary adjustments. <\/p>\n\n\n\n If this knowledge could be integrated into the process, certain operations could be performed more systematically. Work completed once could also serve as a foundation for future adaptations, guided by checks and rules tailored to specific needs. <\/p>\n\n\n\n However, the goal is not merely faster execution; process reliability is also a key factor. Automating certain operations and using specialized agents for verification could minimize redundancy and ensure greater consistency across projects. <\/p>\n\n\n\n Nevertheless, this approach requires maintaining human oversight. The professional remains responsible for the final outcome and must be able to understand the system’s output, the rationale behind specific operations, and any corrections that may be required.<\/p>\n<\/div>Moving from using software to describing an expected result<\/h2>\n\n\n\n
<\/figure><\/div>\n\n\n\nSpecialized agents to meet the demands of XR<\/h2>\n\n\n\n
<\/figure>Save time without eliminating human oversight<\/h2>\n\n\n\n
<\/figure><\/div>\n\n\n\nA new place for 3D expertise<\/h2>\n\n\n\n
![\"\"](\"https:\/\/www.immersion.fr\/wp-content\/uploads\/2026\/10\/I03A0631-retouche-scaled.jpg\")
<\/figure>![\"\"](\"https:\/\/www.immersion.fr\/wp-content\/uploads\/2026\/10\/MCMONIN_00689-2-scaled.jpg\")
<\/figure><\/div>\n","protected":false},"excerpt":{"rendered":"