Ai agent-based analysis of debugging reports for circuit design systems and applications

A system comprising one or more processors to:

• obtain a structured database that includes a set of objects that comprise a plurality of different object structures, the set of objects representing result reports of at least one circuit design analysis;
• obtain an evaluation task input defining one or more sub-tasks directed to the set of objects;
• process the one or more sub-tasks to identify one or more target objects from the set of objects, wherein the one or more sub-tasks are processed based at least on traversing a plurality of nodes of a relation graph, the relation graph comprising a graph structure based at least on the set of objects and at least one debugging trace defining one or more structured strategies for retrieving information from the structured database;
• execute a data retrieval code constructed in response to identification of the one or more target objects, the data retrieval code comprising an algorithm to probe at least a first target object of the one or more target objects based at least on a first sub-task of the one or more sub-tasks directed to the first target object;
• and
• compile an output representing a response to the evaluation task input based at least on a response to the probe of at least the first target object.

A method comprising:

• generating an evaluation task output in response to a query of a structured database including a set of objects comprising a plurality of different object structures and representing result reports of at least one circuit design analysis;
• wherein the evaluation task output is generated based at least on:
• identifying one or more target objects based at least on traversing a plurality of nodes of a relation graph, the relation graph comprising a graph structure based at least on the set of objects and a debugging trace defining one or more structured strategies for retrieving information from the structured database;
• and
• executing a data retrieval code constructed by a language model in response to at least one prompt representing at least one sub-task of the query and an indication of the identified one or more target objects.