Results for "function calling"
Function Calling
IntermediateConstraining model outputs into a schema used to call external APIs/tools safely and deterministically.
Function calling in AI is like giving a computer a specific set of instructions to follow when it needs to get information from another source. Imagine you have a recipe that tells you exactly how to ask a delivery service for ingredients. In AI, function calling ensures that when a model needs t...
Willingness of system to accept correction or shutdown.
Asking model to review and improve output.
Applying learned patterns incorrectly.
Enables external computation or lookup.
Loss of old knowledge when learning new tasks.
Using output to adjust future inputs.
System returns to equilibrium after disturbance.
Predicts next state given current state and action.
Learning physical parameters from data.
Directly optimizing control policies.
Optimizing continuous action sequences.
Reward only given upon task completion.
Learning action mapping directly from demonstrations.
Sampling-based motion planner.
Optimal pathfinding algorithm.
Planning via artificial force fields.
Learning by minimizing prediction error.
Predicting protein 3D structure from sequence.
Predicting borrower default risk.
Agents optimize collective outcomes.
Tendency to gain control/resources.
Goals useful regardless of final objective.
Updating a pretrained model’s weights on task-specific data to improve performance or adapt style/behavior.