Abstract: Conventional testing of artificial intelligence (AI) agents is time-consuming and insufficient. Accordingly, embodiments provide an automated testing and validation framework for the tools utilized by AI agents. The framework may leverage artificial intelligence, including a classifier for classifying tools, a generative model that creates test cases based on the tool classification, an optimization model that maximizes test coverage while minimizing computation cost, an edge-detection model that identifies edge test cases, and/or an execution engine that manages execution of the test suite. The framework may be integrated into a continuous integration and continuous deployment (CI/CI) pipeline.

Abstract: A federated data system enables multiple, independent, decentralized, and autonomous data sources to be queried as if they were a single system. State-of-the art federated data systems suffer from excessive data movement, static execution strategies, and inefficient distributed joins. Disclosed embodiments introduce a multi-agent framework into the federation layer of the federated data system. This agentic framework may comprise a supervisor artificial intelligence (AI) agent that divides queries, from a query engine, into subqueries and utilizes other AI agents to perform sub-tasks, such as rewriting one or more the of the subqueries, determining an execution strategy, executing the subqueries according to the execution strategy, and learning from past query executions. The supervisor AI agent may perform in-memory joins of the results of the subqueries, and return a final query result to the query engine.

Abstract: There is no unified, comprehensive system for the governance of artificial intelligence (AI) agents. Accordingly, disclosed embodiments register a plurality of AI agents, potentially from disparate sources, into a centralized registry. Prior to activation, each AI agent is associated with a governance policy. After activation, each AI agent is monitored in real time, during execution, to determine whether or not the AI agent remains compliant with the associated governance policy. When an AI agent becomes non-compliant with the associated governance policy, corrective action may be taken, and the AI agent may be labeled as untrusted. The corrective action may comprise alerting a user, modifying the AI agent, adjusting an amount of each of one or more computational resources that is allocated to the AI agent, modifying an access of the AI agent to one or more systems, adjusting a communication control of the AI agent, and/or the like.

Abstract: As artificial intelligence (AI) agents become more prevalent, it has become important to measure their effectiveness. Disclosed embodiments enable autonomous, real-time evaluation of AI agents using a monitoring service and peer AI agents. In an embodiment, calls, by a performing AI agent, to models and tools, during a session, are made through respective gateways which collect session data. A monitoring service acquires the session data from the gateways, and invokes one or a plurality of monitoring AI agents to evaluate the performance of the performing AI agent based on the session data and one or more adaptable session parameters. The result of the evaluation(s) may be stored for analysis and development of the performing AI agent.

Abstract: Traditional artificial intelligence (AI) architectures utilize a centralized approach, in which a single large AI model handles all inference tasks. This approach results in high latency, requires significant computational resources, has difficulty adapting to evolving data, and raises privacy concerns. While hybrid AI architectures have been developed, they suffer from static knowledge bases, limited adaptability, and a lack of continuous learning, which reduces their accuracy. Accordingly, embodiments utilize a hybrid architecture with an iterative local-global model feedback loop for continuous learning during inference. In particular, the local model may escalate inputs to the global model, when it is unable to infer a response with sufficient confidence. The global model may provide a global insight, which the local model may integrate into its response and knowledge base.

Abstract: Systems and methods are describe herein for managing a transaction between two parties. A distributed ledger management service (DLMS) microservice receives an electronic document pertaining to a transaction from a user. The electronic document includes transactional data. A document type is determined by the DLMS microservice. A portion of the transactional data is extracted from the electronic document based on the document type. The portion of the transactional data is provided to a distributed ledger node for decentralized storage and further reporting to a third party.

Abstract: Systems and methods are describe herein for managing a transaction between two parties. A distributed ledger management service (DLMS) microservice receives an electronic document pertaining to a transaction from a user. The electronic document includes transactional data. A document type is determined by the DLMS microservice. A portion of the transactional data is extracted from the electronic document based on the document type. The portion of the transactional data is provided to a distributed ledger node for decentralized storage and further reporting to a third party.

Abstract: The invention discloses a novel and efficient drive mechanism for use in a variety of applications. This novel mechanism replaces traditional stepper motors or another analogous art with shape memory alloys. The drive mechanism so disclosed provides substantial operational benefits over conventional motors and other such traditional drive mechanisms that would be used in similar applications. The drive mechanism includes a high gear-ratio worm gear and worm drive which further provides precise, controlled movement of an output shaft. In the illustrative use elaborated upon herein, the motor is used to drive a photovoltaic panel so that the panel may remain in appropriate alignment with the sun throughout the day.

Abstract: The invention discloses a novel and efficient drive mechanism for use in a variety of applications. This novel mechanism replaces traditional stepper motors or another analogous art with shape memory alloys. The drive mechanism so disclosed provides substantial operational benefits over conventional motors and other such traditional drive mechanisms that would be used in similar applications. The drive mechanism includes a high gear-ratio worm gear and worm drive which further provides precise, controlled movement of an output shaft. In the illustrative use elaborated upon herein, the motor is used to drive a photovoltaic panel so that the panel may remain in appropriate alignment with the sun throughout the day.

Abstract: The invention discloses a novel and efficient drive mechanism for use in a variety of applications. This novel mechanism replaces traditional stepper motors or another analogous art with shape memory alloys. The drive mechanism so disclosed provides substantial operational benefits over conventional motors and other such traditional drive mechanisms that would be used in similar applications. The drive mechanism includes a high gear-ratio worm gear and worm drive which further provides precise, controlled movement of an output shaft. In the illustrative use elaborated upon herein, the motor is used to drive a photovoltaic panel so that the panel may remain in appropriate alignment with the sun throughout the day.

Abstract: The present invention provides an apparatus and method for solar tracking. The solar tracking sensor array and method so disclosed can be used with any device that requires a specific orientation to the sun for optimal operation. The system relies upon a sun tracking mechanism which includes a plurality of phototransistors configured in a particular manner. The apparatus can further be used with an analog sensor circuit which is also disclosed herein. Although the device and method are disclosed in conjunction with a solar tracking device, which includes the analog sensor circuit, a drive assembly, and a power source, these components may be used independently of one another.

Abstract: The invention discloses a novel and efficient drive mechanism for use in a variety of applications. This novel mechanism replaces traditional stepper motors or another analogous art with shape memory alloys. The drive mechanism so disclosed provides substantial operational benefits over conventional motors and other such traditional drive mechanisms that would be used in similar applications. The drive mechanism includes a high gear-ratio worm gear and worm drive which further provides precise, controlled movement of an output shaft. In the illustrative use elaborated upon herein, the motor is used to drive a photovoltaic panel so that the panel may remain in appropriate alignment with the sun throughout the day.

Abstract: The present invention provides a motor driven by shape memory alloys for use in a variety of applications. In the disclosed embodiment, the motor is used to drive a photovoltaic panel so that the panel may remain in appropriate alignment with the sun throughout the day. In such a configuration, the motor assembly relies upon the intrinsic properties of shape memory alloys, in conjunction with a spring assembly, in order to generate sufficient torque in order to rotate the photovoltaic panel. In order to control the orientation of the panel, the system relies upon a sun tracking mechanism which includes an analog sensor circuit, a plurality of phototransistors and a power source. Accordingly, the device is able to rotate the photovoltaic panel in discrete and precise increments as the day progresses.

Abstract: A method and system for removing contaminants from contaminated soil at a site utilizes particle size segregation and particle density segregation to yield a plurality of fractions, whereby each of the fractions are tested and identified for the presence of unacceptable levels of contaminants, and the soil fractions from the contaminated soil at the site corresponding to the identified contaminated fractions are collected for subsequent disposal or treatment, while the remaining untainted soil fractions are homogenized and returned to the site.

Abstract: A method and system for removing contaminants from contaminated soil at a site utilizes particle size segregation and particle density segregation to yield a plurality of fractions, whereby each of the fractions are tested and identified for the presence of unacceptable levels of contaminants, and the soil fractions from the contaminated soil at the site corresponding to the identified contaminated fractions are collected for subsequent disposal or treatment, while the remaining untainted soil fractions are homogenized and returned to the site.

Abstract: The invention provides methods for the identification of genes and their encoded proteins involved in the susceptibility to proliferative disorders, including cancer, using a tumor host range mutant virus (T-HR mutant). In addition, the invention provides methods for the diagnosis of abnormally proliferating cells in a subject, using a T-HR mutant. The invention also features, T-HR mutants that can be used to kill cancer cells such as ones carrying a Sal2 alteration. Furthermore, the invention features the analysis of Sal2 nucleic acids and proteins for diagnosing and treating patients having proliferative disorders, including cancer, involving mutations in a Sal2 gene and encoded protein. Also encompassed by the invention are transgenic and knockout mice including Sal2 nucleic acids or proteins and mutants thereof.