Microsoft patents tool that automatically improves AI instructions
Microsoft describes a system that automatically refines the text instructions given to large language models to make them work better. It breaks the instructions into a structured tree format and uses two AI models to test, score, and rewrite specific parts of the text until the output matches the desired result.
In the filing’s own words
The technology described herein automatically tunes large language model (LLM) prompts for improved performance. The system receives an LLM prompt as input, optimizes it, and outputs a more effective prompt. The optimization process involves converting the prompt into a hierarchical prompt tree, which organizes the prompt into distinct sections and subsections. This structured format allows for systematic refinements targeting specific components without altering the entire prompt. The system uses an actor/critic learning model, where the critic evaluates the prompts generated by the actor and provides feedback to guide future prompt generation decisions. The actor executes actions based on the feedback, continuously improving its performance. The iterative process generates replacement prompts, assigns quality scores, and selects high-quality prompts for further optimization.
What exactly they claim (claim 1)
1. One or more computer storage media comprising computer-executable instructions that when executed by computing device performs a method of tuning a prompt, the method comprising: receiving a prompt; generating a hierarchical prompt tree from text in the prompt; providing the hierarchical prompt tree, a large language model (LLM) output generated in response to the prompt combined with an input, and an expected output to a critic model, wherein the input includes actual values that are inserted in placeholders within the prompt; generating, at the critic model, a reflection; providing the reflection and the hierarchical prompt tree of text to an actor model; generating, by the actor model, a revised hierarchical prompt tree; generating a revised prompt from the revised hierarchical prompt tree; and storing the revised prompt.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- AUTOMATIC TUNING OF LLM PROMPTS
- Publication number
- US20260310980A1
- Application number
- 19098084
- Filed
- Apr 2, 2025
- Published
- Oct 8, 2026
- Inventors
- 5
- Claims
- 20
Classified under
G06N 3/092 Physics & computingG06F 16/242 Physics & computingG06N 3/0475 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.