Skip to content
Sagan

Paper

An Empirical Study of Automating Agent Evaluation

Unreadunread

AI summary

The authors investigate whether frontier LLMs can automate the evaluation of AI agents—tasks that involve multi-step reasoning and tool use. They find that simply prompting coding assistants fails badly (30% execution success, over-engineered metrics), so they build EvalAgent, a system that uses "evaluation skills" (procedural instructions, reusable code templates, and API docs) to generate complete evaluation pipelines. They introduce a meta-evaluation benchmark (AgentEvalBench, 20 agents) and an Eval@1 metric measuring whether generated evaluation code runs correctly on the first try.

Main takeaways:

  • Strong coding ability doesn't automatically make LLMs good at building agent evaluations—raw prompting yields only 30% working evaluations.
  • EvalAgent packages domain expertise as "evaluation skills" (instructions, code templates, retrieved docs) and raises Eval@1 from 17.5% to 65%.
  • Human experts prefer EvalAgent's evaluations 79.5% of the time over baseline approaches.
  • Removing the evaluation skills drops Eval@1 back to 30%, showing they're critical for complex evaluation tasks.
  • The system produces focused evaluations instead of metrics bloat (12+ metrics per agent in naive approaches).