Compliant with Local Controls, Collectively Discriminatory. A Governance Architecture for Multi-Agent AI in Regulated Finance
cs.MA, cs.AI
Submitted: 2026-09-23
Updated: 2026-09-23
Terminology
Sources
- Algorithmic Collusion by Large Language Models
- Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
- Emergent Bias and Fairness in Multi-Agent Decision Systems
- Fairness in Agentic AI: A Unified Framework for Ethical and Equitable Multi-Agent System
- Agentic Artificial Intelligence in Finance: A Comprehensive Survey
- Constitutional AI: Harmlessness from AI Feedback
- Deliberative Alignment: Reasoning Enables Safer Language Models
- Let's Verify Step by Step
- Alignment faking in large language models
- AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents
- Responsibility Gap and Diffusion in Sequential Decision-Making Mechanisms
- Everyone Contributes! Incentivizing Strategic Cooperation in Multi-LLM Systems via Sequential Public Goods Games
- Levels of Autonomy for AI Agents
- When Not to Automate: A Formal Protocol for Human Preservation in AI-Optimized Organizations
- MI9: An Integrated Runtime Governance Framework for Agentic AI
- Runtime Governance for AI Agents: Policies on Paths
- When Stress Becomes Signal: Detecting Antifragility-Compatible Regimes in Multi-Agent LLM Systems
Related papers
- Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
- You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
- Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
- MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization
- PeroMAS: A Multi-agent System of Perovskite Material Discovery
- StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning