Lightweight agent router with reduced latency path selection across distributed compute nodes

A non-transitory computer-readable storage medium comprising instructions for dynamically allocating tasks across a plurality of stateless artificial intelligence (AI) agents stored thereon, wherein the instructions when executed by at least one data processor of a system, cause the system to:

• obtain a task request at a computing device communicatively coupled to a plurality of AI agents each operating in a stateless configuration,
• wherein each AI agent is registered in an agent registry configured to store a metadata profile of the AI agent,
• wherein the metadata profile defines a performance metric value set derived from one or more historical task executions associated with the AI agent;
• determine a task feature set from the task request by classifying the task request into one or more task types in accordance with a datastore that maps respective vector representations of one or more historical tasks to one or more historical agent selections;
• generate a score for one or more AI agents of the plurality of AI agents by evaluating the performance metric value set against the task feature set;
• determine an agent configuration by:
• identifying a AI agent subset according to respective scores of the plurality of AI agents, and
• determining an execution order for the AI agent subset by evaluating one or more intermediate output dependencies between one or more sequential portions of the task request;
• cause transmission of the task request to the AI agent subset according to the execution order;
• and
• cause update of the agent registry based on the AI agent subset by:
• obtaining an execution result set responsive to the task request, and
• updating one or more respective performance metric value sets of one or more AI agents based on the execution result set.

A computer-implemented method comprising:

• obtaining a task request at a computing device communicatively coupled to a plurality of AI agents each operating in a stateless configuration,
• wherein each AI agent is registered in an agent registry configured to store a metadata profile of the AI agent,
• wherein the metadata profile defines a performance metric value set derived from one or more historical task executions associated with the AI agent;
• determining a task feature set from the task request by classifying the task request into one or more task types in accordance with a datastore that maps respective vector representations of one or more historical tasks to one or more historical agent selections;
• generating a score for one or more AI agents of the plurality of AI agents by evaluating the performance metric value set against the task feature set;
• determining an agent configuration by:
• identifying a AI agent subset according to respective scores of the plurality of AI agents, and
• determining an execution order for the AI agent subset by evaluating one or more intermediate output dependencies between one or more sequential portions of the task request;
• causing transmission of the task request to the AI agent subset according to the execution order;
• and
• causing update of the agent registry based on the AI agent subset by:
• obtaining an execution result set responsive to the task request, and
• updating one or more respective performance metric value sets of one or more AI agents based on the execution result set.