US-12620019-B2 - System and method enabling application of autonomous agents

US12620019B2US 12620019 B2US12620019 B2US 12620019B2US-12620019-B2

Abstract

Disclosed is system enabling application of autonomous agents (AAs) across problem domains. System comprises decentralised computing network to implement software framework (SF). SF comprises client-agent device (client-AA) to receive service request (SR), generate objective in vector(s) recorded in vector database (VD), send objective to agent-device (AA/micro-AA). Agent-device comprises context-builder software module (CBSM) to send query(-ies) to machine learning model agent (ML-Model AA) and/or access VD to retrieve task(s) associated with previous queries to obtain tasks associated with objective. CBSM to obtain order of task execution from ML-Model AA, to obtain list including AAs, to block communication signals between client-AA and AAs not associated with objective, to associate AA(s) with task(s); protocol generator software module comprising domain-independent protocol specification language (DIPSL) generate protocol specification(PS(s)) for task execution by AA(s); build executor software module compose task(s) in order, compose AA into further autonomous agent (further-AA), encrypt access to further-AA, further-AA implement PS(s) to execute each task and SR.

Inventors

Humayun Munir Sheikh
Attila Bagoly
Edward Fitzgerald

Assignees

ASSMBL.AI LIMITED
UVUE Ltd.

Dates

Publication Date: 20260505
Application Date: 20230517

Claims (14)

1 . A system for enabling application of autonomous agents (AAs) across a plurality of problem domains, the system comprising: a decentralized computing network configured to implement a software framework, wherein the software framework comprises a plurality of modular and extensible software modules configured to operate as a plurality of autonomous agents (AAs) within a plurality of computing devices, wherein the plurality of autonomous agents (AAs) are communicably coupled with each other, wherein the software framework comprises: a client-agent device (client-AA) comprising a software application configured: to receive a service request and to generate an objective associated with the service request, wherein when generating the objective associated with the service request, the software application is configured to employ at least one data processing algorithm to match metadata associated with previous service requests with at least one service that is requested in the service request, to extract content from the match, and to transform the extracted content in form of one or more vectors recorded in vector database, wherein the objective is in the form of one or more vectors recorded in the vector database, and to send the objective to an agent-device (AA or micro-AA), wherein the agent-device (AA or micro-AA) comprises: a context-builder software module configured to, upon receiving the objective, send one or more queries to a machine learning model agent (ML-Model AA) and to access the vector database to retrieve one or more tasks associated with previous queries in order to obtain a plurality of tasks associated with the objective, wherein the context-builder software module is further configured to interactively communicate with the machine learning model agent (ML-Model AA) to obtain an order in which each task is to be executed, wherein the order is dynamically determined based on at least one of availability, cost, or user preferences, wherein the context-builder software module is further configured to interactively communicate with the machine learning model agent (ML-Model AA) to: obtain, using a registry component comprising a database of autonomous agents and their components and a search and discovery component, a list including a plurality of autonomous agents (AAs or micro-AAs) that are capable of performing the plurality of tasks and that are associated with the objective, block communication signals between the client-agent device (client-AA) and autonomous agents which are not associated with the objective, and associate at least one autonomous agent from the plurality of autonomous agents associated with the objective with at least one task and such that each task is associated with at least one autonomous agent associated with the objective; a protocol generator software module comprising a domain-independent protocol specification language which, upon receiving an invocation from the context-builder software module, is configured to generate at least one protocol specification for the execution of each task by the at least one autonomous agent associated with the task, wherein the protocol specification is generated using the domain-independent protocol specification language; and a build executor software module configured to: compose the at least one task in the order dynamically determined by the context-builder software module based on insights from the machine learning model agent (ML-Model AA), wherein the insights are derived from the previous queries and previous task executions recorded in the vector database, compose each autonomous agent associated with the objective into a further autonomous agent (further-AA) by combining capabilities and functionalities of each autonomous agent associated with the objective from the registry component, and encrypt access to the further autonomous agent to prevent tampering, wherein the further autonomous agent (further-AA) is configured to implement the at least one protocol specification to execute each task associated with the objective through the decentralized computing network and thereby automatically execute the service request.
2 . The system of claim 1 , wherein when generating the objective associated with the service request, the software application is configured to: refer the service request to a Large Language Model (LLM) for processing, wherein the Large Language Model (LLM) is configured to transform the service request into a service data associated with the service request, the service data being in the form of one or more vectors recorded in the vector database; and use the service data received from the Large Language Model (LLM) as the objective.
3 . The system of claim 2 , wherein the Large Language Model (LLM) is at least one of: an internal Large Language Model (Internal-LLM) of the client-agent device (client-AA), an external Large Language Model (Internal-LLM) of or associated with the agent-device (AA or micro-AA).
4 . The system of claim 1 , wherein the service request is received from at least one of: a software application executing on a device of a user, a software application executing on a computing device that is communicably coupled to a device of a user, a cloud-based software application, a digital twin of a user, a digital representation of a user, an artificial intelligence model (AI-model) based on a Large Language Model (LLM).
5 . The system of claim 1 , wherein the machine learning model agent (ML-Model AA) is at least one of: an internal Large Language Model (Internal-LLM) of the agent-device (AA or micro-AA), an external Large Language Model (Internal-LLM) associated with the agent-device (AA or micro-AA).
6 . The system of claim 1 , wherein the context-builder software module is further configured to send a list of the plurality of tasks associated with the objective, to a device of a user; and receive, from the device, an input indicative of at least one of: which tasks amongst the plurality of tasks are to be executed, an order in which each task amongst said tasks is to be executed.
7 . The system of claim 1 , wherein the components of the autonomous agents comprise at least one of: skills, protocols, connections, of the autonomous agents.
8 . A method for enabling application of autonomous agents (AAs) across a plurality of problem domains, the method comprising: receiving, at a client-agent device (client-AA) comprising a software application, a service request and generating an objective associated with the service request, wherein generating the objective associated with the service request comprises employing, by the software application, at least one data processing algorithm to match metadata associated with previous service requests with at least one service that is requested in the service request, to extract content from the match, and to transform the extracted content in form of one or more vectors recorded in vector database, wherein the objective is in the form of one or more vectors recorded in the vector database, sending the objective from the client-agent device (client-AA) to an agent-device (AA or micro-AA), wherein a software framework comprises the client-agent device (client-AA) and the agent-device (AA or micro-AA), and wherein the software framework is implemented using a decentralized computing network, and wherein the software framework comprises a plurality of modular and extensible software modules configured to operate as a plurality of autonomous agents (AAs) comprised within a plurality of computing devices, wherein the plurality of autonomous agents (AAs) are communicably coupled with each other, sending one or more queries from a context-builder software module of the agent-device (AA or micro-AA) to a machine learning model agent (ML-Model AA) and accessing the vector database to retrieve one or more tasks associated with previous queries in order to obtain a plurality of tasks associated with the objective, wherein the context-builder software module further implements a step of interactively communicating with the machine learning model agent (ML-Model AA) for obtaining an order in which each task is to be executed, the order is dynamically determined based on at least one of availability, cost, or user preferences, and the context-builder software module further implements a step of interactively communicating with the machine learning model agent (ML-Model AA) for: obtaining, using a registry component comprising a database of autonomous agents and their components and a search and discovery component, a list including a plurality of autonomous agents (AAs or micro-AAs) that are capable of performing the plurality of tasks and that are associated with the objective, blocking communication signals between the client-agent device (client-AA) and autonomous agents which are not associated with the objective, and associating at least one autonomous agent from the plurality of autonomous agents associated with the objective with at least one task and such that each task is associated with at least one autonomous agent associated with the objective; generating at least one protocol specification for the execution of each task by the at least one autonomous agent associated with the task, upon receiving an invocation from the context-builder software module, using a protocol generator software module of the agent-device (AA or micro-AA), the protocol generator software module comprising a domain-independent protocol specification language, wherein the protocol specification is generated using the domain-independent protocol specification language; and composing the at least one task, using a build executor software module of the agent-device (AA or micro-AA), in the order dynamically determined by the context-builder software module based on insights from the machine learning model agent (ML-Model AA), wherein the insights are derived from the previous queries and previous task executions recorded in the vector database, composing each autonomous agent associated with the objective into a further autonomous agent (further-AA) by combining capabilities and functionalities of each autonomous agent associated with the objective from the registry component, and encrypting access to the further autonomous agent to prevent tampering, wherein the further autonomous agent (further-AA) implements the at least one protocol specification for executing each task associated with the objective through the decentralized computing network and thereby automatically executes the service request.
9 . The method of claim 8 , wherein the step of generating the objective associated with the service request comprises: referring the service request to a Large Language Model (LLM) for processing, wherein the Large Language Model (LLM) implements a step of transforming the service request into a service data associated with the service request, the service data being in the form of one or more vectors recorded in the vector database; and using the service data received from the Large Language Model (LLM) as the objective.
10 . The method of claim 9 , wherein the Large Language Model (LLM) is at least one of: an internal Large Language Model (Internal-LLM) of the client-agent device (client-AA), an external Large Language Model (Internal-LLM) of or associated with the agent-device (AA or micro-AA).
11 . The method of claim 8 , wherein the service request is received from at least one of: a software application executing on a device of a user, a software application executing on a computing device that is communicably coupled to a device of a user, a cloud-based software application, a digital twin of a user, a digital representation of a user, an artificial intelligence model (AI-model) based on a Large Language Model (LLM).
12 . The method of claim 8 , wherein the machine learning model agent (ML-Model AA) is at least one of: an internal Large Language Model (Internal-LLM) of the agent-device (AA or micro-AA), an external Large Language Model (Internal-LLM) associated with the agent-device (AA or micro-AA).
13 . The method of claim 8 , wherein the method further comprises: sending, from the context-builder software module, a list of the plurality of tasks associated with the objective, to a device of a user; and receiving, at the context-builder software module, an input indicative of at least one of: which tasks amongst the plurality of tasks are to be executed, an order in which each task amongst said tasks is to be executed.
14 . The method of claim 8 , wherein the components of the autonomous agents comprise at least one of: skills, protocols, connections, of the autonomous agents.

Description

TECHNICAL FIELD The present disclosure relates generally to systems that, in operation, enable application of autonomous agents (AAs) across plurality of problem domains. The present disclosure also relates to methods for enabling application of autonomous agents (AAs) across plurality of problem domains. BACKGROUND Autonomous agents (AAs) have gained significant attention in recent years as a promising technology for addressing complex tasks across various problem domains. The autonomous agents (AAs) possess the ability to perceive their environment, make decisions, and take actions autonomously, thereby reducing the need for direct human intervention. However, existing systems that employ autonomous agents face several limitations and challenges that hinder their widespread adoption and effectiveness. Traditional centralized architectures often struggle to handle large-scale deployments of the autonomous agents. As the number of autonomous agents and the complexity of tasks increase, the centralized control and communication become bottlenecks, leading to performance degradation and inefficiencies. Moreover, coordinating the actions of numerous autonomous agents operating in a decentralized manner becomes increasingly difficult, impeding the system's ability to effectively solve complex problems. Existing systems often lack robust mechanisms for agents to collaborate and exchange information seamlessly. This hinders their ability to work together on interconnected tasks or to transfer knowledge between the autonomous agents, limiting their overall problem-solving capabilities. Additionally, the lack of standardized protocols and frameworks for agent coordination poses interoperability challenges and inhibits the development of versatile and flexible multi-agent systems. The existing systems often lack robust mechanisms for handling security and safety concerns. Moreover, the autonomous agents of the existing systems fail to understand a service request completely, thereby leading to a failure in fulfilling the service request obtained from a user. Furthermore, the existing autonomous agents misinterpret queries or fail to recognize context. The existing autonomous agents often struggle with understanding and maintaining context during extended conversations or interactions. The existing autonomous agents may fail to remember previous queries, responses, or user preferences, resulting in disjointed and less effective interactions. The existing autonomous agents struggle with tasks that involve multi-step processes, require creative thinking, or demand comprehensive domain knowledge. Therefore, in light of the foregoing technical problems, there exists a need to overcome the aforementioned problems associated with existing autonomous agents (AAs). SUMMARY The present disclosure seeks to provide a system that, in operation, enables application of autonomous agents (AAs) across a plurality of problem domains. The present disclosure also seeks to provide a method for enabling application of autonomous agents (AAs) across plurality of problem domains. An aim of the present disclosure is to provide a solution that overcomes at least partially the problems encountered in prior art. DESCRIPTION OF EMBODIMENTS The following detailed description illustrates embodiments of the present disclosure and ways in which they can be implemented. Although some modes of carrying out the present disclosure have been disclosed, those skilled in the art would recognize that other embodiments for carrying out or practicing the present disclosure are also possible. In one aspect, the present disclosure provides a system that, in operation, enables application of autonomous agents (AAs) across a plurality of problem domains, the system comprising a decentralised computing network configured to implement a software framework, wherein the software framework comprises a plurality of modular and extensible software modules configured to operate as a plurality of autonomous agents (AAs) comprised within a plurality of computing devices, wherein the plurality of autonomous agents (AAs) are communicably coupled with each other, wherein the software framework comprises: a client-agent device (client-AA) comprising a software application configured: to receive a service request and to generate an objective associated with the service request, wherein the objective is in a form of one or more vectors recorded in a vector database, and to send the objective to an agent-device (AA or micro-AA), wherein the agent-device (AA or micro-AA) comprises: a context-builder software module configured to, upon receiving the objective, send one or more queries to a machine learning model agent (ML-Model AA) and/or to access the vector database to retrieve one or more tasks associated with previous queries in order to obtain a plurality of tasks associated with the objective, wherein the context-builder software module is further configured to interactive