Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents

TL;DR

Agentic CLEAR is a novel evaluation framework that provides automated, multi-level insights into LLM agent behavior, improving over static, limited tools by offering dynamic, data-driven feedback.

Contribution

It introduces an automatic, adaptable evaluation system for LLM agents that operates across multiple levels and integrates seamlessly with existing tools.

Findings

High-quality, data-driven insights into agent behavior.

Strong alignment with human error annotations.

Ability to predict task success rate.

Abstract

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited, focusing on observability with basic evaluation capabilities or imposing static, hand-crafted error taxonomies that cannot adapt to new domains. To address this gap, we present Agentic CLEAR, an automatic, dynamic, and easy-to-use evaluation framework. It produces textual insights into the agent behavior on three levels of granularity: system, trace, and node. Agentic CLEAR operates above the observability layer, enabling seamless integration and featuring an intuitive UI that makes agent evaluation highly accessible. In our experiments on four benchmarks, seven agentic settings, and tens of thousands of LLM calls, we show that Agentic CLEAR produces high-quality, data-driven, insightful feedback. Our analysis shows strong alignment with human-annotated errors and the ability to predict task success rate.