Google patents search that builds a research outline before answering
This filing describes a system that takes a complex search question and first creates a structured plan, or research outline, with main topics and sub-topics. It then runs multiple specific searches based on that plan and combines the results into a single, summarized answer.
In the filing’s own words
Systems and methods for research-and-synthesis searches can include obtaining a search query, determining the search query is associated with a research-and-synthesis task, generating a model-generated research outline, performing a plurality of searches based on the model-generated research outline, and generating a model-generated response based on the search query, research outline, and search results. The systems and methods can generate the model-generated research outline and the model-generated response with a generative model that interfaces with external tools to obtain the relevant search results.
What exactly they claim (claim 1)
1. A computer-implemented method, the method comprising: obtaining, by a computing system comprising one or more processors, a search query; processing, by the computing system, the search query with a generative model to generate a research outline, wherein the research outline comprises an overview topic prompt and a plurality of sub-topic prompts associated with a topic of the overview topic prompt; generating, by the computing system and with the generative model, a plurality of model-generated queries based on the research outline, wherein the plurality of model-generated queries comprises a first model-generated query associated with the overview topic prompt and a plurality of second model-generated queries associated with the plurality of sub-topic prompts; performing, by the computing system and based on the plurality of model-generated queries, a plurality of searches to determine a plurality of search results sets, wherein each of the plurality of search results sets are associated with a different model-generated query of the plurality of model-generated queries; processing, by the computing system, the search query, the research outline, and at least a subset of each set of the plurality of search results sets with the generative model to generate a model-generated research synthesis, wherein the model-generated research synthesis comprises a distillation of information identified from at least the subset of each set of the plurality of search results sets determined to be responsive to the overview topic prompt and the plurality of sub-topic prompts; and providing, by the computing system, the model-generated research synthesis for display.
Facts
- Company
- Google (Google LLC)
- Official title
- Generative Agentic System for Processing Multi-Task Queries
- Publication number
- US20260310701A1
- Application number
- 19557893
- Filed
- Mar 5, 2026
- Published
- Oct 8, 2026
- Inventors
- 3
- Claims
- 24
Classified under
G06F 16/334 Physics & computingG06F 16/3326 Physics & computingG06F 16/35 Physics & computingG06F 16/358 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 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.
