Abstract: In one implementation, a device receives a natural language input for processing by a first agent executed by the device. The first agent generates, based on the natural language input, an output in a first embedding space using an artificial intelligence model. The first agent identifies a second agent for further processing of the output. The first agent provides the first agent, the output for further processing by a second agent.

Abstract: In one embodiment, a method comprises: parsing, using a large language model, a constraint satisfaction problem statement into a sequence of sentences corresponding to a plurality of individual problem sentences and a plurality of individual answer choices; invoking respective primitives from a set of logical-linguistic primitive functions to iteratively process i) each of the plurality of individual problem sentences to establish a respective problem constraint with accompanying arguments and ii) each of the plurality of individual answer choices to establish a respective answer choice constraint with accompanying arguments; storing, during invoking, the respective problem constraints into an aggregate list of problem constraints; and solving, after completion of the aggregate list of problem constraints, the constraint satisfaction problem statement as a validity output for each answer choice constraint given the aggregate list of problem constraints.

Abstract: In one embodiment, a method for a cache-generated frequently asked questions page includes converting a received query into a set of embeddings and performing a semantic searching operation based on information contained in the set of embeddings against a cache of question and answer pairs. The method further includes returning a stored answer to the received query responsive to a determination that a particular question and answer pair in the cache of question and answer pairs meets a threshold similarity level for the information contained in the set of embeddings, the stored answer derived from the particular question and answer pair and performing a large language model operation to generate an answer to the query responsive to a determination that no question and answer pair in the cache of question and answer pairs meets the threshold similarity level for the information contained in the set of embeddings.

Abstract: In one embodiment, a method herein may comprise: fetching relevant context responsive to a particular query initially submitted into a large language model without additional context; determining that an output from the large language model for the particular query is an unacceptable output; providing, responsive to the unacceptable output, a select portion of the relevant context to the large language model for a subsequent output; and increasing, progressively and responsive to subsequent unacceptable outputs from the large language model, an amount of context in each subsequent portion iteratively provided to the large language model until an acceptable output is achieved.

Abstract: In one embodiment, a method herein comprises: obtaining, by a device, one or more modular natural language processing pipelines each having a respective plurality of selected pipeline stage components; processing, by the device, an input text by the one or more modular natural language processing pipelines to produce an output from each of the one or more modular natural language processing pipelines; generating, by the device, benchmarking metrics regarding each output processed from each of the one or more modular natural language processing pipelines; and providing, by the device, the benchmarking metrics on a visual dashboard interface for assessment of the benchmarking metrics corresponding to each of the one or more modular natural language processing pipelines.

Abstract: In one embodiment, a method comprises: parsing, using a large language model, a constraint satisfaction problem statement into a sequence of sentences corresponding to a plurality of individual problem sentences and a plurality of individual answer choices; invoking respective primitives from a set of logical-linguistic primitive functions to iteratively process i) each of the plurality of individual problem sentences to establish a respective problem constraint with accompanying arguments and ii) each of the plurality of individual answer choices to establish a respective answer choice constraint with accompanying arguments; storing, during invoking, the respective problem constraints into an aggregate list of problem constraints; and solving, after completion of the aggregate list of problem constraints, the constraint satisfaction problem statement as a validity output for each answer choice constraint given the aggregate list of problem constraints.

Abstract: In one embodiment, a method for a cache-generated frequently asked questions page includes converting a received query into a set of embeddings and performing a semantic searching operation based on information contained in the set of embeddings against a cache of question and answer pairs. The method further includes returning a stored answer to the received query responsive to a determination that a particular question and answer pair in the cache of question and answer pairs meets a threshold similarity level for the information contained in the set of embeddings, the stored answer derived from the particular question and answer pair and performing a large language model operation to generate an answer to the query responsive to a determination that no question and answer pair in the cache of question and answer pairs meets the threshold similarity level for the information contained in the set of embeddings.

Abstract: In one embodiment, a method herein comprises: extracting topics from queries submitted into a large language model; determining a quality of outputs from the large language model in response to the queries; assessing per-topic performance of the large language model across the topics queried into the large language model based on the quality of the outputs; determining one or more underperforming topics for the large language model based on the per-topic performance of the large language model across the topics; and performing one or more mitigation actions based on the one or more underperforming topics for the large language model. In one implementation, the method comprises: displaying a user interface that indicates the per-topic performance of the large language model across the topics as a heatmap, and delineating the one or more underperforming topics specifically within the heatmap.

Abstract: Method and capability to yield gesture-based, touchless communication between user and electronic device. The system identifies hand or finger gestures by utilizing depth-mapping-based camera sensor technology, eliminating the necessity of a touch or hover sensitive device. With the use of an inertial measurement unit or similar gyroscopic sensor(s), the system will be portable and be able to function as a wearable, In particular implementations, “mouse movement gestures”, “pinch gestures”, “twist gestures”, and other gestures of the like can, but are not limited to, be used to provide input, actuate commands, manipulate display(s), and allow access to applications.

Abstract: Method and capability to yield gesture-based, touchless communication between user and electronic device. The system identifies hand or finger gestures by utilizing depth-mapping-based camera sensor technology, eliminating the necessity of a touch or hover sensitive device. With the use of an inertial measurement unit or similar gyroscopic sensor(s), the embodiment of the present disclosure embodiment will be portable and be able to function as a wearable, In particular implementations, “mouse movement gestures”, “pinch gestures”, “twist gestures”, and other gestures of the like can, but are not limited to, be used to provide input, actuate commands, manipulate display(s), and allow access to applications.