# Multi-Agent Framework for Audit Risk Assessment with Explicit Uncertainty and Evidence Conflict Modeling

arXiv: https://arxiv.org/abs/2606.15640 · HTML: https://mlsanity.com/paper/2606.15640/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 5 of its 27 references that are in the map.
- First posted on arXiv 14 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, 5 of 5)

- [Contrastive Learning-Based Dependency Modeling for Anomaly Detection in Cloud Services](https://mlsanity.com/paper/2510.13368/) (2025)
- [EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements](https://mlsanity.com/paper/2506.08762/) (2025)
- [Artificial Intelligence-Based Multiscale Temporal Modeling for Anomaly Detection in Cloud Services](https://mlsanity.com/paper/2508.14503/) (2025)
- [Improving Pattern Recognition of Scheduling Anomalies through Structure-Aware and Semantically-Enhanced Graphs](https://mlsanity.com/paper/2512.18673/) (2025)
- [Joint Temporal-Structural Representation Learning for Distributed Fault Discrimination in Microservice Architectures](https://mlsanity.com/paper/2605.01776/) (2026)

## Abstract (arXiv)

Audit risk assessment increasingly benefits from combining heterogeneous evidence sources, yet existing approaches typically produce point predictions without quantifying how well different evidence streams agree. We propose UMAR (Uncertainty-Aware Multi-Agent Risk Assessment), a framework that employs three specialized agents: an MD&A Text Agent, a Financial Ratio Agent, and a CAM Agent, each producing independent risk scores with calibrated uncertainty estimates. An Uncertainty Aggregator based on Dempster-Shafer evidence theory fuses these scores while explicitly measuring inter-agent conflict. We evaluate UMAR on a U.S. dataset of 3,200 firm-year observations from SEC 10-K filings (2019-2023), with financial restatement as the target label. Experimental results show that UMAR achieves an AUROC of 0.782 and a PR-AUC of 0.341, outperforming logistic regression, XGBoost, FinBERT, and single-agent and dual-agent LLM baselines. UMAR attains the lowest expected calibration error (ECE = 0.052) among all methods and identifies evidence-conflict patterns that correlate with actual restatement risk, offering auditors potentially actionable and interpretable risk signals.