# AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification

arXiv: https://arxiv.org/abs/2606.03031 · HTML: https://mlsanity.com/paper/2606.03031/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [FinSage: A Multi-aspect RAG System for Financial Filings Question Answering](https://mlsanity.com/paper/2504.14493/) (2025)
- [ToolGate: Contract-Grounded and Verified Tool Execution for LLMs](https://mlsanity.com/paper/2601.04688/) (2026)
- [FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs](https://mlsanity.com/paper/2510.08886/) (2025)
- [Enhancing Financial Question Answering with a Multi-Agent Reflection Framework](https://mlsanity.com/paper/2410.21741/) (2024)
- [OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG](https://mlsanity.com/paper/2601.09028/) (2026)
- [Grounding LLM Reasoning with Knowledge Graphs](https://mlsanity.com/paper/2502.13247/) (2025)
- [RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QA](https://mlsanity.com/paper/2508.09893/) (2025)
- [Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification](https://mlsanity.com/paper/2603.02798/) (2026)
- [FinRule-Bench: A Benchmark for Joint Reasoning over Financial Tables and Principles](https://mlsanity.com/paper/2603.11339/) (2026)
- [Structured Debate Improves Corporate Credit Reasoning in Financial AI](https://mlsanity.com/paper/2510.17108/) (2025)

## Built on by (most cited first, 2 of 2)

- [IntelliAudit: Using Large Language Models to Evaluate Audit Controls](https://mlsanity.com/paper/2608.07688/) (2026)
- [Fin_Agent at FinEval 2026: Task-Aware Methods for Multilingual Financial NLP](https://mlsanity.com/paper/2610.14101/) (2026)

## Abstract (arXiv)

Structured financial reporting verification requires connecting reported facts to accounting constraints, reconstructing expected values, and executing numerical checks. We study this problem through XBRL numerical consistency verification and introduce textscAuditFlow, a graph-grounded multi-agent framework built around an executable symbolic environment. The environment links a reusable US-GAAP taxonomy graph with filing-specific XBRL evidence and provides typed tools for retrieval, traversal, computation, and rule evaluation. Two specialized auditors investigate constraints and filing evidence, while a senior auditor coordinates disagreement-triggered refinement. Deterministic tools produce verification evidence; evidential aggregation combines structured reports, including agent-declared overrides, into final decisions. On a newly collected 1,000-instance evaluation set of engine-recorded DQC violations, textscAuditFlow achieves 87.70% joint audit accuracy with Claude Sonnet 4.6, compared with 68.60% for Single Agent and 86.70% for Checker-only. Component and coverage analyses identify executable verification as the main source of accuracy, while additional gains from agent judgment depend on the backbone and checker coverage.