AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification

• URL: http://arxiv.org/abs/2606.03031v1
• Date: Tue, 02 Jun 2026 02:14:42 GMT
• Title: AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification
• Abstract summary: AuditFlow is a graph-grounded multi-agent framework that separates adaptive search from verification.<n>Two junior auditors inspect each case from regulatory and evidentiary views, while a senior auditor resolves disagreements and can request further investigation.<n>Final reports are fused through evidential aggregation to produce an audit verdict, expected value, evidence trail, and score.
• Score: 19.94244675257689
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• VERA-8B: Evidence-Grounded Audit Risk Reasoning from SEC Filings [0.6445605125467574]
  We develop VERA-8B, a new end-to-end audit reasoning system.<n> VERA-8B identifies audit risks before enforcement actions occur.<n>We are the first to unify SFT and GRPO for evidence-grounded audit reasoning.
  arXiv  Detail & Related papers  (2026-08-28T14:55:49Z)
• Auditable by Construction: An Ontology-Driven Framework for Trustworthy LLM Analytics in Enterprise Finance [0.0]
  This paper argues that retrieval-augmented generation for enterprise finance should be evaluated on auditability alongside accuracy.<n>We present the Knowledge-Driven Analytics Framework (KDAF), which builds ontology-driven knowledge systems through six iterative stages.<n>An evaluation on FinanceBench (145 questions) compares KDAF against zero-context inference, BM25, concept-weighted lexical retrieval, and ungrounded graph traversal.
  arXiv  Detail & Related papers  (2026-08-21T01:35:34Z)
• AuditWeave: A Tamper-Evident, Auditor-Navigable Evidence Layer for AI-Assisted and Data-Transformation Workflows [0.0]
  AuditWeave is a lightweight Python library that records the steps of AI-assisted and data-transformation into a single hash-chained ledger.<n>We describe the design and evaluate recording overhead, scalability, and tamper-detection correctness on the reference implementation.
  arXiv  Detail & Related papers  (2026-06-14T21:46:04Z)
• FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search [88.16262636915975]
  FineVerify is a fine-grained self-verification framework for agentic search.<n>It decomposes each question into checkable sub-questions, verifies sampled candidates, and selects the candidate with the highest aggregated score.<n>FineVerify consistently outperforms standard scaling baselines.
  arXiv  Detail & Related papers  (2026-05-30T10:21:20Z)
• Auditable Decision Models with Learned Abstention and Real-Time Steering [6.287457666346811]
  Production AI systems often operate with incomplete, conflicting, or insufficient evidence.<n>We study operational decision control for AI systems, where uncertainty must be explicitly routable.<n>We present EvaluatorDPT, a bounded decision-control model that predicts YES, NO, or TBD.
  arXiv  Detail & Related papers  (2026-05-26T23:37:56Z)
• Targeted Tests for LLM Reasoning: An Audit-Constrained Protocol [0.9805949492148788]
  We propose an audit-constrained protocol for targeted reasoning evaluation.<n>We instantiate Component Prompt Sampling (CAPS), a score-based deterministic sampler over prompt components, and compare it with equal-budget uniform component sampling.
  arXiv  Detail & Related papers  (2026-05-12T06:26:22Z)
• Automated Population-Level Audit Assurance via AI-Based Document Intelligence [0.0]
  Audit transaction testing validates accuracy and completeness of customer-facing statements against internal systems of record.<n>Traditional manual, sample-based review of unstructured PDF statements is labor-intensive and does not scale to millions of transactions.<n>This paper presents an automated framework for large-scale audit transaction testing using AI-based document intelligence.
  arXiv  Detail & Related papers  (2026-05-05T19:17:18Z)
• FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosures [39.77510496944984]
  We present FinReporting, an agentic workflow for localized cross-jurisdiction financial reporting.<n>The system builds a unified canonical ontology over Income Statement, Balance Sheet, and Cash Flow.<n>It decomposes reporting into auditable stages including filing acquisition, extraction, canonical mapping, and anomaly logging.
  arXiv  Detail & Related papers  (2026-04-07T15:00:01Z)
• IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation [49.796717294455796]
  We present IMMACULATE, a practical auditing framework that detects economically motivated deviations.<n>IMMACULATE selectively audits a small fraction of requests using verifiable computation, achieving strong detection guarantees while amortizing cryptographic overhead.
  arXiv  Detail & Related papers  (2026-02-26T07:21:02Z)
• HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam [63.84155758655084]
  Humanity's Last Exam (HLE) has become a widely used benchmark for evaluating frontier large language models.<n>We introduce HLE-Verified, a verified and revised version of HLE with a transparent verification protocol and fine-grained error taxonomy.<n>We evaluate seven state-of-the-art language models on HLE and HLE-Verified, observing an average absolute accuracy gain of 7--10 percentage points.
  arXiv  Detail & Related papers  (2026-02-15T02:50:15Z)
• Preventing the Collapse of Peer Review Requires Verification-First AI [49.995126139461085]
  We propose truth-coupling, i.e. how tightly venue scores track latent scientific truth.<n>We formalize two forces that drive a phase transition toward proxy-sovereign evaluation.
  arXiv  Detail & Related papers  (2026-01-23T17:17:32Z)
• Auditing Fairness under Model Updates: Fundamental Complexity and Property-Preserving Updates [18.205253587709525]
  We study group fairness auditing under arbitrary updates.<n>We propose a generic framework for PAC auditing based on an Empirical Property Optimization (EPO) oracle.
  arXiv  Detail & Related papers  (2026-01-09T16:28:11Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers [121.53749383203792]
  We present a holistic end-to-end solution for annotating the factuality of large language models (LLMs)-generated responses. We construct an open-domain document-level factuality benchmark in three-level granularity: claim, sentence and document. Preliminary experiments show that FacTool, FactScore and Perplexity are struggling to identify false claims.
  arXiv  Detail & Related papers  (2023-11-15T14:41:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.