# 微软等提出 AgentScope：用行为抽象和神经不变量定位智能体失败步骤

- 来源：DAIR.AI (@dair_ai)
- 发布时间：2026-09-05 02:00
- AIHOT 分数：44
- AIHOT 链接：https://aihot.virxact.com/items/cmtnafv5e01jkrog17gfqcsvj
- 原文链接：https://x.com/dair_ai/status/2095934975489282223

## AI 摘要

微软等机构发布论文提出 AgentScope，一个用于诊断智能体失败的神经符号系统。它把智能体行为从轨迹抽象成结构化表示，再用 LLM 校验的自然语言神经不变量描述行为属性，从而同时定位失败步骤和失败类型；在公开的 Who&When 数据集和作者自建的 AgentErrata 数据集上，故障定位与归因准确率显著优于现有最优方法。

## 正文

Insightful paper from Microsoft and colleagues.

If you have ever had an agent run fail 80 steps ago with no way to find where, this one is for you.

(bookmark it)

Agent failures show up as long complex trajectories. Traditional software debugging techniques do not apply here, and handing the whole trace to an LLM judge produces unreliable diagnoses.

AgentScope is a neuro-symbolic diagnosis system addressing this issue. Agent behavior is abstracted from its trajectory into a structured representation, so the search happens over program-like objects instead of prose.

Behavior properties are then written as neural invariants, specifications stated in natural language that an LLM checks against the abstraction.

That combination identifies both the failing step and its failure type. It significantly outperforms the current state of the art in fault localization and attribution accuracy on the public Who&When dataset and on AgentErrata, a broader failure dataset the authors built.

Paper: https://arxiv.org/abs/2609.02371

Chat with Paper: https://academy.dair.ai/papers/diagnosing-with-insights-structured-analysis-of-agent-failures-via-behavioral-ab-2609.02371