Governance at the Boundary: How Agent Decomposition Degrades Policy Compliance

2026-08-16

AI Summary

This study addresses the compliance degradation arising from agent component decomposition by introducing Fiducia-bench, the first governance benchmark for financial agents. Through KYC/AML tasks and comparative experiments across multiple architectures, this work reveals a novel mechanism wherein boundary information attenuation within orchestration frameworks leads to compliance failures. Notably, factual decay rates reach 85% and are significantly modulated by model capabilities. Furthermore, the research elucidates the correlation between architectural complexity and governance costs, providing critical mechanistic insights into agent compliance risks. By open-sourcing both the dataset and validation framework, this work fills a significant gap in evaluating financial agent governance, establishing a foundational resource for future research on compliant autonomous systems in regulated domains.

Abstract

Existing agent benchmarks ask whether the agent finished the task. We ask whether it finished it within policy. We introduce Fiducia-bench, a benchmark for the governability of financial agents---whether they escalate when obligated, abstain when required, and leave an auditable trail---and use it to study a question no prior benchmark addresses: does decomposing an agent into components degrade its governance? It does, and the mechanism is specific. Policy-relevant facts discovered by one component are attenuated at the handoff boundary before reaching the component that must act on them. In a 626-episode experiment across 100 KYC/AML task variants, two models, and three architectures, a 32B open-weights model attenuated 0% of discovered facts under a single-loop baseline, 56% under a fixed pipeline, and 85% under an orchestrator-subagent architecture (all at constraint distance 2). A stronger model (gpt-4.1-mini) attenuated 3-6% under the same conditions, suggesting the governance cost of decomposition is partly a function of model capability. Critically, the same mechanism produces both under-escalation and over-escalation, depending on whether the dropped fact was a risk signal or an exculpating one. The benchmark, all tasks, and the verification harness are open-source

Problem

• Agent Decomposition
• Policy Compliance
• Governability
• Information Attenuation
• Financial Agents

Innovation

• Fiducia-bench
• Agent Decomposition
• Policy Compliance
• Information Attenuation
• Financial Agents