Evaluation of agent systems requires different approaches than traditional software or even standard language model applications. Agents make dynamic decisions, are non-deterministic between runs, and often lack single correct answers. Effective evaluation must account for these characteristics while providing actionable feedback. A robust evaluation framework enables continuous improvement, catches regressions, a...
Agent evaluation requires outcome-focused approaches that account for non-determinism and multiple valid paths. Multi-dimensional rubrics capture various quality aspects: factual accuracy, completeness, citation accuracy, source quality, and tool efficiency. LLM-as-judge provides scalable evaluation while human evaluation catches edge cases.
The key insight is that agents may find alternative paths to goals—the evaluation should judge whether they achieve right outcomes while following reasonable processes.
Этот навык следует использовать, когда пользователь просит «оценить производительность агента», «построить структуру тестирования», «измерить качество агента», «создать критерии оценки» или упоминает LLM в качестве судьи, многомерную оценку, тестирование агента или контрольные параметры качества для конвейеров агентов. Источник: guanyang/antigravity-skills.