Nvidia patents AI system to organize and query complex circuit debug reports
Nvidia describes a system that uses machine learning agents to turn messy circuit design reports into a structured database. It creates a map of how these reports connect, allowing the system to break down user questions into smaller tasks and automatically write code to find the right answers.
In the filing’s own words
In various examples, machine learning model agent-based analysis of debugging reports for circuit design systems and applications is disclosed. A multi-file report analysis agent may analyze the original structure of individual timing reports to construct a structured report database for the set of reports. Based on the individual reports incorporated into the structured report database, the report analysis agent may construct a TDRG that connects the individual reports based on relationships. An MCMM planner agent may decompose the user-provided evaluation task inputs into sub-tasks for multiple corners and modes and call a TDRG traversal agent to resolve individual sub-tasks, as indicated by a mode plan. The TDRG traversal agent prompts expert report agents to retrieve information from the structural report database based on traversing the TDRG. An expert report agent may generate data retrieval code that may be executed to query the specified report from the structured report database.
What exactly they claim (claim 1)
1. One or more processors comprising processing circuitry to: generate a structured database based at least on a set of objects comprising a plurality of different object structures, the set of objects representing result reports of at least one circuit design analysis; construct, based at least on the set of objects, a relation graph comprising a plurality of nodes and a plurality of edges, wherein an individual node of the plurality of nodes corresponds to an individual object of the set of objects, and an individual edge of the plurality of edges indicates a relationship between objects as indicated by at least one debugging trace; decompose an evaluation task input into a mode plan including a plurality of subtasks directed to the set of objects; process the plurality of sub-tasks based at least on traversing the plurality of nodes of the relation graph to identify one or more target objects from the set of objects; construct data retrieval code comprising an algorithm to query a first target object of the one or more target objects based at least on a first sub-task of the plurality of subtasks directed to the first target object; execute the data retrieval code to generate a response to the query of the first target object; and generate an output comprising a response to the evaluation task input based at least on the response to the query of the first target object.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- AI AGENT-BASED ANALYSIS OF DEBUGGING REPORTS FOR CIRCUIT DESIGN SYSTEMS AND APPLICATIONS
- Publication number
- US20260310869A1
- Application number
- 19172330
- Filed
- Apr 7, 2025
- Published
- Oct 8, 2026
- Inventors
- 3
- Claims
- 20
Classified under
G06F 30/3315 Physics & computingG06F 30/27 Physics & computingMore from Nvidia in AI & software
- Nvidia patents AI coach that analyzes your gameplay to suggest strategies Oct 13, 2026
- Nvidia patents AI system that writes and voices character conversations Sep 10, 2026
- Nvidia patents system that uses AI to find bugs in game videos Sep 17, 2026
- Nvidia patents AI method to make digital characters move realistically Sep 8, 2026
- Nvidia patents AI system that builds image generators from text prompts Sep 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.