Abstract: A system and a method for allocating limited resources to agents that reveal their stochastic demands on arrival over a finite horizon in a proportionally fair manner that exhausts available resource budgets are provided. The allocation of limited resources includes receiving a request for a resource for which a predetermined maximum amount of the resource is available for allocation during a predetermined time interval, and estimating a number of future requests expected to be received and amounts of the resource to be requested within the predetermined time interval. The initial estimates are then adjusted by calculating a standard deviation of an uncertainty of at least one future request, and an amount of the resource to allocated to a resource requesting entity is determined by applying an algorithm with respect to the adjusted estimates and the predetermined maximum available amount of the resources.

Abstract: Various methods and processes, apparatuses or systems, and media for performing a link prediction of a missing node in a knowledge graph are disclosed. The present disclosure provides acquiring the knowledge graph and extracting a set of information from the knowledge graph, the set of information indicates data entities and edges. Each of the edges indicates a relationship between a pair of data entities. The method further includes identifying triplets included in the knowledge graph, in which each of the triplets includes a pair of nodes connected by an edge, and generating an ontological graph model based on the triplets identified and the acquired knowledge graph. The method further performs, via the LLM, a link prediction for the missing node of the knowledge graph based on the generated ontological graph model.

Abstract: A method and system for generating a response to a user prompt may be provided. The method may include obtaining the user prompt comprising the at least one objective and the at least one user preference dimension. The method may include performing an inference of the user prompt via the combination ML model, the combination ML model may include a base large language model (LLM) and at least one autoregressive reward model (ARM). The method may include generating the response corresponding to the at least one objective correlating with the at least one user preference dimension via the combination ML model.

Abstract: Various methods and processes, apparatuses/systems, and media for automated structure retrieval of complex standard operating procedures (SOPs) are disclosed. A processor encodes the SOP as a Directed Acyclic Graph (DAG) to keep track of the dependencies between SOP tasks or steps and retain the sequential aspect of the SOP execution. To be able to support long SOPs, the processor implements a multi-phase approach where the processor first performs a “segmentation” step to break the SOP into task segments which are then transformed into a DAG by calling a structure generation module. The segmentation is utilized recursively to attain a fined-grain decomposition of the SOP to facilitate effective DAG generation.

Abstract: A system for implementing a resource transmission management tool that processes resource transmissions, the system comprising a processor that is configured to: obtain a first set of requests that comprises a first resource transmission request; transform the first resource transmission request into a first corresponding encoded resource request; generate, by organizing an arrangement of at least the first corresponding encoded resource request, a pre-processed set of requests that comprises the first corresponding encoded resource request; assign, based on a topology of the pre-processed set of requests, a respectively corresponding weight to each transmission request field; analyze the first corresponding encoded resource request according to associated instructions; and generate a response to the associated instructions based on the analysis.

Abstract: A method and a system for using a large language model (LLM) to automatically translate textual instructions into executable software code via skill distillation and composition are provided. The method includes: receiving a request for performing a task and a prompt; providing, as an input to an LLM, the first request and a response to the prompt; receiving, from the LLM, a set of code that implements a function that corresponds to a skill that is usable for performing the task; generating a test that relates to the task; performing the test by executing the set of code and checking whether the task has been successfully completed; and when the task has been successfully completed, storing the set of code in a skills library. Sets of code stored in the skills library may then be accessed and combined in order to perform larger tasks.

Abstract: A method and system for verifying a structured query language (SQL) query are provided. The method includes: receiving a first request to retrieve first data that is accessible via a database; identifying an intention of the first request; generating, based on the first request, a first SQL query to retrieve the first data from the database; predicting, based on the generated first SQL query, an output of the generated first SQL query; determining whether the predicted output matches the identified intention of the first request; generating, based on the determining of whether the predicted output matches the identified intention of the first request, a second SQL query to retrieve the first data that is accessible via the database, when the predicted output of the first SQL query does not match the identified intention of the first request.

Abstract: A system for implementing a resource transmission management tool that processes resource transmissions, the system comprising a processor that is configured to: obtain a first set of requests that comprises a first resource transmission request; transform the first resource transmission request into a first corresponding encoded resource request; generate, by organizing an arrangement of at least the first corresponding encoded resource request, a pre-processed set of requests that comprises the first corresponding encoded resource request; assign, based on a topology of the pre-processed set of requests, a respectively corresponding weight to each transmission request field; analyze the first corresponding encoded resource request according to associated instructions; and generate a response to the associated instructions based on the analysis.

Abstract: Systems and methods for risk-sensitive reinforcement learning are disclosed. In one embodiment, a method for a method for training a risk-sensitive reinforcement learning policy may include: (1) receiving, from a data source, a plurality of sets of training data for a plurality of time steps; (2) receiving a training budget comprising a plurality of episodes, a risk aversion coefficient, and an end state; and (3) calculating a correction factor using the training data. The correction factor may minimize stochasticity based on a risk aversion coefficient.

Abstract: A method and a system for obtaining an evaluation of a quality of software code that is generated by using a large language model (LLM) are provided. The method includes: receiving a set of instructions for performing a task and generating an output; providing, as an input to an LLM, a list of available application programming interfaces (APIs) and the instructions, together with a submission of a request to the LLM to select one API and to generate a set of executable code based on the instructions; receiving, from the LLM, a selection of one API and the set of executable code; executing the set of executable code in order to perform the first task and generate the output; and evaluating an accuracy, a robustness, and/or a consistency of the set of executable code.

Abstract: A method and system for performing a task requiring a plurality of sequential decision-making operations by an autonomous agent are disclosed. The method includes acquiring a portion of offline data from a database, and discovering a set of separate skills. The method further includes segmenting the offline data and segmenting the offline data according to skill, and abstracting the segmented offline data into reusable functions. From the abstracted reusable functions, distilling primitives for each skill and distilling reusable tips in various functions. Modifying skill based text-based and code-based policies for augmenting the autonomous agent, and processing a task requiring a set of sequential decision-making operations using the augmented autonomous agents.

Abstract: Aspects of the subject disclosure may include, for example, identifying source equipment is associated with a group of recipient equipment based on historical financial data, and determining a processing latency between the source equipment and each recipient equipment of the group of recipient equipment based on the historical financial data. Further embodiments can include determining a processing rate for each processing latency, and determining a verification latency to perform security authentication for each recipient equipment. Additional embodiments can include determining a verification rate for each verification latency, determining a service metric based on the processing rates and the verification rates, the service metric being associated with a token service that expediates a transfer of financial data between the source equipment and the group of recipient equipment, and presenting the service metric at the source equipment to enroll in the token service. Other embodiments are disclosed.

Abstract: A method for creating a realistic agent-based simulation of an over-the-counter market and using data from the real market to calibrate the simulator is provided. The method includes: assigning, to each of a group of agents, a type value that relates to a state of the respective agent; receiving agent-specific data that relates to market-based observations, market-based actions, and market-based rewards; generating a market simulation based on the assigned type values and the received agent-specific data; and calibrating the market simulation based on actual market data.

Abstract: A system and a method for allocating indivisible resources to agents over a finite horizon in a manner that balances resource utilization and fairness are provided. The method includes: receiving first information that relates to a number of agents included in a set of agents; receiving second information that relates to whether each respective agent is requesting an allocation of an indivisible resource during a particular allocation round; assigning, to each respective agent, a respective weight that relates to an importance of the respective agent; calculating, for each respective agent, a respective agent-specific allocation probability; and determining an allocation of the indivisible resource for the particular allocation round based on the agent-specific allocation probabilities. The determination of the allocation may be adjusted based on a budget that indicates an availability of the resource during the particular allocation round.

Abstract: A method and system for performing information-directed pessimism in offline learning for reduction of distribution mismatch are disclosed. The method includes determining a first and second distribution for the ML model based on different datasets, and determining a presence of a distribution mismatch between the first distribution and the second distribution. The method further includes calculating a value for an individual state-action pair in a training dataset and comparing the calculated value against a reference data distribution, determining a difference between the calculated value and the reference data distribution and comparing the difference against a reference threshold.

Abstract: A method and system for accounting for missing not-at-random (MNAR) data in training dataset via Bayesian regularization are disclosed. The method includes acquiring historical data of an organization, the historical data including the MNAR data. The method further includes performing estimation for two of at least three unknown quantities based on the historical data, and injecting quantitative information for remaining one of the at least three unknown quantities based on qualitative information regarding nature of missingness. Lastly, the method reassembles the estimation for two of the at least three unknown quantities and injected quantitative information for the remaining one of the at least three unknown quantities, to provide a modified function.

Abstract: A method for providing a synthetic neural data model is disclosed. The method includes generating a model that simulates an electronic communication network; appending agents to the model, the agents relating to a software component that sends orders to the model based on a predetermined timestep; assigning a fixed grid to the model, the fixed grid including a tick size that relates to a fixed granularity; calibrating each of the agents by using a calibration data set; inputting the model and historical book data to a neural network; and training, via the neural network, a neural network extension of the model by using an optimizer.

Abstract: A system and a method for allocating limited resources to agents that reveal their stochastic demands on arrival over a finite horizon in a proportionally fair manner that exhausts available resource budgets are provided. The method includes: receiving, from an entity, a request for a resource for which a predetermined maximum amount of the resource is available for allocation; estimating a number of future requests and amounts of the resource to be requested within a predetermined time interval; adjusting a result of the estimating by calculating a standard deviation of an uncertainty of at least one future request; and determining, based on the estimates and the adjustment, an amount of the resource to allocated to the entity by applying an algorithm with respect to the adjusted estimates and the predetermined maximum available amount of the resources.

Abstract: A method for creating a realistic agent-based simulation of an over-the-counter market and using data from the real market to calibrate the simulator is provided. The method includes: assigning, to each of a group of agents, a type value that relates to a state of the respective agent; receiving agent-specific data that relates to market-based observations, market-based actions, and market-based rewards; generating a market simulation based on the assigned type values and the received agent-specific data; and calibrating the market simulation based on actual market data.

Abstract: Systems and methods for risk-sensitive reinforcement learning are disclosed. In one embodiment, a method for a method for training a risk-sensitive reinforcement learning policy may include: (1) receiving, from a data source, a plurality of sets of training data for a plurality of time steps; (2) receiving a training budget comprising a plurality of episodes, a risk aversion coefficient, and an end state; and (3) calculating a correction factor using the training data. The correction factor may minimize stochasticity based on a risk aversion coefficient.