mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
6089446f04
* wip * wip * wip * wip * wip * wip * Update docs/design/main.md Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> * Update docs/design/main.md Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> * wip * wip * wip * wip * wip * wip * wip * wip * wip * update * update * update * wip * wip * wip * wip * address comment * update * add custom agent example * address comment * update code teaser * Update docs/design/main.md Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> * update * address comments * update guardrails * address some of mark's comments * add new separate sections for agents and workflows * update agent doc * Update agent.md Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com> * add foundry agent doc * wip * refine the component registration interface with agent runtime * update * workflows * update * update * Update * Update * update * Update design doc to remove runtime * Update * Update * Update * update * Add eval section notes (#9) * add notes on eval * remove duplicate title * update docs * update docs * save updates before merge * update evaluation script * Update agents.md * update workflows * Update Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com> * update workflow * Updated design doc * Update * Update * update * update * Update * update * update * Update * update * Update with agent abstraction alternatives * Update discussion * Update * update * Update * Update * Update * Update --------- Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com> Co-authored-by: Victor Dibia <chuvidi2003@gmail.com>
345 B
345 B
Optimization and Tuning
For future consideration.
The framework should support optimization of agents and workflows with task feedback, by tuning the various components such as system prompts, model parameters, and tool configurations.
We should also consider fine-tuning of the models and embeddings as part of the optimization process.