# 智能体CLEAR：LLM智能体多层级评估自动化

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-21 08:00
- AIHOT 分数：57
- AIHOT 链接：https://aihot.virxact.com/items/cmpnz3nhf01iqslv4io0ishtp
- 原文链接：https://arxiv.org/abs/2605.22608

## AI 摘要

现有LLM智能体评估工具局限于基本观测能力或静态错误分类。Agentic CLEAR是一个自动、动态、易用的评估框架，它在系统、轨迹和节点三个粒度层级上，对智能体行为生成文本洞察。该框架运行于可观测性层之上，具备直观UI便于集成。在四个基准、七种智能体设置和数万次LLM调用上的实验表明，Agentic CLEAR能产生高质量、数据驱动的反馈，其分析与人类标注错误高度吻合，并能预测任务成功率。

## 正文

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.