AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification
On the map: LLM agents and tool use → Financial trading and forecasting agents
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.
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.
Builds on
17 of 29 references.
Closest ancestors · 2
Same direction, newest first
- 2025Structured Debate Improves Corporate Credit Reasoning in Financial AI20 Oct
- 2024Enhancing Financial Question Answering with a Multi-Agent Reflection Framework29 Oct
Other references · 15
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
- 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
- 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
- 2025FinSage: A Multi-aspect RAG System for Financial Filings Question Answeringcited by 19
- 2026ToolGate: Contract-Grounded and Verified Tool Execution for LLMscited by 15
- 2025FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMscited by 14
- 2026OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAGcited by 11
- 2025Grounding LLM Reasoning with Knowledge Graphscited by 7
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2026FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosures
- 2025FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models
- 2026CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA
- 2026LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents
- 2026FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification
- 2026FinRCA-Bench: Benchmarking Evidence Retrieval and Reasoning for Financial AI Systems
- 2025FinVet: A Collaborative Framework of RAG and External Fact-Checking Agents for Financial Misinformation Detection
- 2026LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing