Microsoft patents AI system that guesses your hidden preferences
Microsoft describes a multi-agent AI system that takes your input and uses a generative model to search data for relevant information. It then analyzes this data to infer preferences you did not explicitly state, using those guesses to guide how the AI performs tasks. The filing focuses on how the system learns from the combination of your input and the retrieved data to tailor its actions.
In the filing’s own words
In some examples, input is provided to a first input augmentation sub-agent of a multi-agent system and input augmentation data is received from the first input augmentation sub-agent. The input augmentation data includes an aggregation of query results generated by an execution of a query on a dataset. The query is formulated by a generative machine learning model (GMLM) in response to a code generation instruction. The code generation instruction is formulated by the first input augmentation sub-agent in response to the input. The aggregation of query results is formulated by the GMLM in response to the execution of the query. A learning including a machine learning-based representation of the input and the input augmentation data is generated. The learning is used to determine a non-explicit user preference. The non-explicit user preference is used to control execution of a task according to the non-explicit user preference.
What exactly they claim (claim 1)
1. A computer-implemented method comprising: providing input received via a device and user metadata to a first input augmentation sub-agent of a multi-agent system; receiving input augmentation data from the first input augmentation sub-agent, wherein the input augmentation data comprises an aggregation of query results generated by an execution of a query on a dataset, wherein the query is formulated by a generative machine learning model (GMLM) in response to a code generation instruction, wherein the code generation instruction is formulated by the first input augmentation sub-agent in response to the input and the user metadata, and wherein the aggregation of query results is formulated by the GMLM in response to the execution of the query; generating a learning, wherein the learning comprises an embedding of the input augmentation data received from the first input augmentation sub-agent; inferring a non-explicit user preference based on the input and the learning; and sending the non-explicit user preference to a task agent of the multi-agent system to control execution of a task according to the non-explicit user preference.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- AGENTIC ARTIFICIAL INTELLIGENCE-BASED INPUT AUGMENTATION
- Publication number
- US20260267868A1
- Application number
- 19075693
- Filed
- Mar 10, 2025
- Published
- Sep 10, 2026
- Inventors
- 5
- Claims
- 20
Classified under
G06F 16/248 Physics & computingG06F 16/243 Physics & computingMore from Microsoft in AI & software
- Microsoft patents method to check AI answers against verified facts Oct 20, 2026
- Microsoft patents AI that presents PowerPoint slides for you Sep 3, 2026
- Microsoft patents method to check if LLM answers are based on real data Sep 10, 2026
- Microsoft patents system to blend multiple AI agents into one chat Oct 1, 2026
- Microsoft patents system that answers questions using your screen history Oct 15, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.