Autonomous Agent Competency Assessment for Reliable Task Decomposition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing machine learning systems struggle with breaking down complex tasks into plausible and workable sub-steps, often leading to incorrect or unrealistic outcomes due to over-confidence.

Innovation Solution

A machine learning powered autonomous agent system that breaks tasks into manageable sub-steps, accesses a database or external information sources to enhance competency, and uses simulation tools to validate sub-step execution, reducing the likelihood of hallucinations and improving operational accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the control breaks the command into sub-steps and determines competency for each sub-step, then the reliability of task execution is improved, but the device complexity increases

Engineering Contradiction:
Improvetask execution reliabilityVSAvoidcontrol system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The control system segments complex commands into multiple sub-steps, evaluating competency for each sub-step individually. This segmentation allows the system to identify specific areas of uncertainty without requiring complete task decomposition, balancing reliability improvement with manageable complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary competency determination mechanism that acts as a mediator between command reception and execution. This intermediary layer evaluates whether the control is competent to perform each sub-step, providing a structured approach to reliability assessment without overwhelming system complexity.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If the control seeks additional information from stored data or external sources when incompetent, then the accuracy of sub-step execution is improved, but the loss of time increases

Engineering Contradiction:
Improvesub-step execution accuracyVSAvoidinformation retrieval time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by maintaining stored data and external information sources ready for access. When competency is determined to be insufficient, the system can quickly retrieve necessary information without extensive search, reducing the time penalty for accuracy improvement.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms where the results of information retrieval and competency assessment feed back into future decision-making. This feedback loop enables the system to learn from past information needs, optimizing future information retrieval efficiency while maintaining high execution accuracy.

Inventive Principle:
Principle #23Feedback

3Adaptability or versatility

If the control uses machine learning to improve operation over time, then the adaptability to diverse tasks is improved, but the device complexity increases

Engineering Contradiction:
Improvetask adaptabilityVSAvoidmachine learning system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The control system performs self-service through machine learning, automatically improving its operation and competency assessments over time without requiring external reconfiguration. The system learns from its experiences and stored data, enhancing task adaptability while managing complexity through autonomous self-improvement mechanisms.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4667169A1Machine learning powered autonomous agent system for competency self-assessment and improvement
Publication Date: 2025.12.24 RTX CORP
  • EP4667169A1 patent drawingFigure 1
  • EP4667169A1 patent drawingFigure 2
  • EP4667169A1 patent drawingFigure 2A

AI summary

A system for controlling a tool includes a tool operable to perform tasks. A control for the tool includes processing circuitry for using machine learning to improve operation of the tool, and having access to a memory with stored data. The processing circuitry is operable to communicate with a user interface, and the user interface is operable to provide a prompt for a desired action to the control. The control is operable to break the received prompt into a plurality of sub-steps, communicate with the stored data, and make a determination as to whether the control is competent to perform each of the sub-steps. The control is operable to control the tool to perform one of the sub-steps if it has determined it is competent and to communicate to other information if it determines it is not competent to perform any others of the sub-steps. A method is also disclosed.