tuning

Definition

Adjusting something that already exists so it fits a target. The word covers two distinct activities: fine-tuning, which updates a pretrained model's weights on new data, and hyperparameter tuning, which searches over settings like learning rate and batch size without changing the method. Context disambiguates. Either way the contrast is with pre-training, which builds broad capability from scratch; tuning shapes what is already there.

Explainers using this term

• Paper Walkthrough: DART-SD — Training Tool-Calling Agents Without Flattening the DiamondDART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents
• Paper Explained: Agentic ESOpt — Drop Backprop, Jiggle the Weights, and Train Long-Horizon LLM AgentsAgentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements