# Compliant with Local Controls, Collectively Discriminatory. A Governance Architecture for Multi-Agent AI in Regulated Finance

arXiv: https://arxiv.org/abs/2609.27994 · HTML: https://mlsanity.com/paper/2609.27994/

## 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 17 of its 41 references that are in the map.
- First posted on arXiv 23 Sep 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)

- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [Collective Constitutional AI: Aligning a Language Model with Public Input](https://mlsanity.com/paper/2406.07814/) (2024)
- [Secret Collusion among AI Agents: Multi-Agent Deception via Steganography](https://mlsanity.com/paper/2402.07510/) (2024)
- [Algorithmic Collusion by Large Language Models](https://mlsanity.com/paper/2404.00806/) (2024)
- [Levels of Autonomy for AI Agents](https://mlsanity.com/paper/2506.12469/) (2025)
- [AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents](https://mlsanity.com/paper/2506.04018/) (2025)
- [Runtime Governance for AI Agents: Policies on Paths](https://mlsanity.com/paper/2603.16586/) (2026)
- [Fairness in Agentic AI: A Unified Framework for Ethical and Equitable Multi-Agent System](https://mlsanity.com/paper/2502.07254/) (2025)
- [Emergent Bias and Fairness in Multi-Agent Decision Systems](https://mlsanity.com/paper/2512.16433/) (2025)
- [Everyone Contributes! Incentivizing Strategic Cooperation in Multi-LLM Systems via Sequential Public Goods Games](https://mlsanity.com/paper/2508.02076/) (2025)
- [Responsibility Gap and Diffusion in Sequential Decision-Making Mechanisms](https://mlsanity.com/paper/2507.02582/) (2025)
- [When Stress Becomes Signal: Detecting Antifragility-Compatible Regimes in Multi-Agent LLM Systems](https://mlsanity.com/paper/2605.02463/) (2026)
- [When Not to Automate: A Formal Protocol for Human Preservation in AI-Optimized Organizations](https://mlsanity.com/paper/2607.15944/) (2026)

## Abstract (arXiv)

Financial institutions are beginning to deploy agentic workflows in credit, fraud, collections, compliance, and operational control. Governance remains largely component-centric: each model or agent is specified, tested, authorized, and monitored locally. That is insufficient when institutional risk arises from the joint behavior of many locally acceptable components. We call this gap constitutional non-compositionality: local compliance checks need not compose into acceptable collective outcomes such as bounded disparate impact, market integrity, or traceable accountability. We propose ARIA as a finance-specific reference architecture and falsifiable research agenda for agent-population governance. It organizes six capabilities across normative-accountability, execution-control, and assurance-learning planes: policy specification, population-level observed-versus-expected behavior monitoring (M2), bounded authority, runtime containment, adaptive policy change, and preserved human oversight competence. Two simulations illustrate shared-signal thin-file exclusion under local controls and earlier warning from observed-versus-expected distributional monitoring in a constructed drift regime. The contribution maps these controls to fair-lending, EU AI Act, model-risk, and conduct-supervision evidence needs, and closes with a validation agenda rather than a production-effectiveness claim.