The Agentic AI Framework for Optimizing Yield Aggregators in Decentralized Finance

AI Governance for Institutional Readiness in Finance

This work proposes a four-layer framework (Policy, Engineering, Composition, Systemic) grounded in two distinct kinds of evidence, kept explicitly separate, and provides a 90-day implementation sequence spanning trading and payments/customer-facing systems.

Governing Agentic AI in FinTech

Financial institutions are delegating consequential decisions to agentic AI systems that decompose goals, coordinate models and tools, and act with little oversight. Yet agentic AI governance in FinTech is under-investigated. We argue the binding governance constraint is not capability but verifiability. We define the Verifiability Gap as the shortfall between the verification delegated authority demands and the explainability and reproducibility retained after a decision. It is indexed to a verifier, evidentiary standard, and audit lag. We develop a multilevel governance theory for agentic AI and test its mechanisms in three studies over nine model versions, from a three-billion-parameter local model to a commercial frontier system. Study 1 shows that provider releases alter historical financial actions, and that the controls replay needs belong to the provider: the frontier model rejects temperature, top_p and top_k outright and exposes no random seed. Under the tightest controls each endpoint allows, a local model reproduced 320 of 320 executions, hosted models 319 of 320 and 959 of 960. Study 2 shows that orchestration is a latent policy layer. Architecture changes final actions, and no execution record repeated in any configuration at any scale. The frontier model reproduces its own actions more often than the local ones, its record no better, and loses a comparable share of its differentiation. Capability buys a higher starting point, not auditability. Study 3 shows two deterministic credit-model versions each reproduce their current action perfectly, yet the current cannot recover a historical one. We conceptualize reproducibility as a governance profile, not a scalar, yielding evidence-contingent delegation: authority is defensible only while retained evidence substantiates its exercise. Beyond finance, the framework extends to other high-stakes domains requiring auditability.

A Multi-Agent AI Framework for Explainable and Low-Latency Investment Analytics in Structured Finance

Structured finance environments generate large volumes of heterogeneous, dynamic, and time-sensitive financial data, creating significant challenges for investment analytics, risk assessment, and decision-making. Many traditional investment intelligence systems are built on a centralized architecture, which has scalability, transparency, and real-time responsiveness challenges. To overcome these problems, this paper suggests a multi-agent artificial intelligence framework for explainable and low-latency investment analytics in structured finance. Its structure is based on the concept of a community of smart agents responsible for gathering financial information, creating market knowledge, valuing risk, predicting, explaining, and optimizing investments. The orchestration layer helps to coordinate interactions between agents and enables parallel processing of agents, leading to more efficient and responsive analysis. The high-tech machine learning models are integrated with the Explainable Artificial Intelligence (XAI) mechanisms and produce clear, interpretable, and meaningful investment tips. It is an active system that is constantly analyzing financial data and can predict market trends and patterns and give good insights into investments without sacrificing transparency of investment decisions. The performance of the proposed framework on investment analytics is validated experimentally, which shows significant improvement in the performance of the investment analytics and an investment prediction accuracy of 97.3%. Furthermore, the framework reduces the latency of processing and guarantees the transparency, scalability, and reliability of decision-making. The results indicate that the suggested solution has the potential for offering an efficient and reliable solution for future-generation investment analytics using a structured finance environment.

Agentic Empirical Asset Pricing: Methodological Foundations

This work evaluates SEADS against five re-implemented baselines on two US equity panels using this standard: no single metric ranks the systems consistently, motivating evaluation on multiple axes at once.

Leveraging generative AI for granular credit data utilization: a multi-agent approach 1

Agentic AI Orchestration of Heterogeneous Economic Models for Rapid, Multi-scenario Analysis of Energy Crises

Rigorous economic models can take months to construct, yet energy crises demand decisions from policymakers within days or even hours. Any disruption in energy markets is not isolated but rapidly disseminates through interlinked global systems. Off-the-shelf models that already exist typically focus only on limited aspects of the system and are distributed across research groups, programming languages, software architectures not designed for model integration, and incompatible formats. Integrating these models manually can take longer than the crisis itself, forcing analysts to rely on whichever models are easiest to connect and leaving consequential scenarios unexplored. Policymakers must make rapid decisions with obstructed and limited information. We show that large language models can perform the critical integration directly. The system constructs internally consistent scenarios, translates assumptions into model-specific inputs, executes existing economic and physical models in dependency order, and synthesizes outputs tailored to policymakers. The language model generates no quantitative results: every reported value is reproduced directly from an underlying model run, remains traceable to its source and is subject to analyst approval at each stage. We develop a LLM framework that coordinates 16 models of oil, natural gas, shipping, water, helium, fertilizer and macroeconomic equilibrium. The framework is applied across five scenarios to assess the 2026 closure of the Strait of Hormuz and refreshed weekly for eight weeks as events on the ground continued to unfold. By linking models that already exist and reading them as a suite rather than in isolation, this architecture mobilizes distributed scientific models rapidly during energy and geopolitical disruptions while keeping any single model's assumptions from driving the conclusion.