# AuditFlow：用于结构化财务报告验证的可执行符号环境

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-02 08:00
- AIHOT 分数：60
- AIHOT 链接：https://aihot.virxact.com/items/cmpyw41oa03vnsli305nkxvwv
- 原文链接：https://arxiv.org/abs/2606.03031

## AI 摘要

AuditFlow是图基多智能体框架，分离自适应搜索与确定性验证。从静态US-GAAP分类图和动态XBRL申报图构建符号环境，提供事实检索、分类遍历、数值检查和规则评估工具。两初级审计员从监管与证据视角检查案例，高级审计员解决分歧并请求进一步调查，最终证据聚合生成审计裁决、预期值、证据链和可信度分数。在FinAuditing衍生的FinMR样本上，使用GPT-5.5达82.09%联合审计准确率，比最强基线高14.93个百分点。移除确定性检查后准确率降至17.91%，表明符号环境执行了模型无法可靠替代的验证步骤。

## 正文

Structured financial audit verification is difficult for language-model agents because correctness depends on structured evidence rather than text alone. A model must link reported facts to taxonomy concepts, traverse calculation or dimensional relations, and recompute expected values before applying an audit rule. We propose AuditFlow, a graph-grounded multi-agent framework that separates adaptive search from deterministic verification. AuditFlow builds a symbolic environment from a static US-GAAP taxonomy graph and a dynamic XBRL filing graph, and exposes it through typed tools for fact retrieval, taxonomy traversal, numerical checking, and rule evaluation. Two junior auditors inspect each case from regulatory and evidentiary views, while a senior auditor resolves disagreements and can request further investigation. The final reports are fused through evidential aggregation to produce an audit verdict, expected value, evidence trail, and trustworthiness score. On a FinAuditing-derived FinMR sample, AuditFlow reaches 82.09% joint audit accuracy under GPT-5.5, outperforming the strongest baseline by 14.93 points. Removing deterministic checks drops accuracy to 17.91%, showing that the symbolic environment performs the verification step that the model cannot reliably replace.