Oculi: A Conversational Agentic Platform for Automated Credit Risk Analysis

• URL: http://arxiv.org/abs/2608.28944v1
• Date: Fri, 28 Aug 2026 23:29:01 GMT
• Title: Oculi: A Conversational Agentic Platform for Automated Credit Risk Analysis
• Abstract summary: Oculi is a conversational platform that transforms natural language questions into comprehensive credit risk analyses.<n>Oculi employs a three-layer architecture that separates reasoning (LLM-powered agent), execution (Model Context Protocol tool servers), and presentation (agentic UI)
• Score: 3.9479959948925356
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Credit risk analysis in financial institutions traditionally requires analysts to manually write SQL queries, run statistical computations, and build visualization dashboards. This is a time-consuming workflow that limits exploration to familiar segments. We introduce \textbf{Oculi}, a conversational platform that transforms natural language questions into comprehensive credit risk analyses, complete with data queries, statistical testing, and interactive visualizations. Oculi employs a three-layer architecture that separates reasoning (LLM-powered agent), execution (Model Context Protocol tool servers), and presentation (agentic UI), enabling analysts to discover high-risk portfolio segments. Within Oculi, a new segment discovery pipeline is proposed that combines deterministic statistical methods with LLM-guided feature selection, leveraging LLM semantic domain knowledge alongside data-driven metrics to identify meaningful, actionable portfolio segments. Evaluated on a mortgage portfolio with 200+ features, Oculi demonstrates effectiveness in discovering material risk segments previously intractable through manual exploration, reducing time-to-insight significantly while maintaining auditability and statistical rigor.

Related papers

• Agentic Interpretation: Lattice-Structured Evidence for LLM-Based Program Analysis [2.1833756646187763]
  We propose agentic interpretation, a framework that brings the discipline of lattice-based static analysis to program reasoning.<n>A worklist algorithm governs how claims and their judgments evolve during the analysis.
  arXiv  Detail & Related papers  (2026-05-12T19:46:24Z)
• PMAx: An Agentic Framework for AI-Driven Process Mining [44.712128560040384]
  We present PMAx, an autonomous agentic framework that functions as a virtual process analyst.<n>Rather than relying on LLMs to generate process models or compute analytical results, PMAx employs a privacy-preserving multi-agent architecture.
  arXiv  Detail & Related papers  (2026-03-16T14:35:39Z)
• CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency [60.83660377169452]
  This paper introduces CryptoBench, the first expert-curated, dynamic benchmark designed to rigorously evaluate the real-world capabilities of Large Language Model (LLM) agents.<n>Unlike general-purpose agent benchmarks for search and prediction, professional crypto analysis presents specific challenges.
  arXiv  Detail & Related papers  (2025-11-29T09:52:34Z)
• Exploratory Semantic Reliability Analysis of Wind Turbine Maintenance Logs using Large Language Models [0.0]
  This paper addresses the gap in leveraging modern large language models (LLMs) for more complex reasoning tasks.<n>We introduce an exploratory framework that uses LLMs to move beyond classification and perform semantic analysis.<n>The results demonstrate that LLMs can function as powerful "reliability co-pilots," moving beyond labelling to synthesise textual information and actionable, expert-level hypotheses.
  arXiv  Detail & Related papers  (2025-09-26T14:00:20Z)
• FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering [57.18367828883773]
  FinAgentBench is a benchmark for evaluating agentic retrieval with multi-step reasoning in finance.<n>The benchmark consists of 26K expert-annotated examples on S&P-500 listed firms.<n>We evaluate a suite of state-of-the-art models and demonstrate how targeted fine-tuning can significantly improve agentic retrieval performance.
  arXiv  Detail & Related papers  (2025-08-07T22:15:22Z)
• Data-to-Dashboard: Multi-Agent LLM Framework for Insightful Visualization in Enterprise Analytics [2.7933239275667545]
  We present an agentic system that automates the data-to-dashboard pipeline through modular LLM agents.<n>Unlike existing chart systems, our framework simulates the analytical reasoning process of business analysts.<n>Our approach shows improved insightfulness, domain relevance, and analytical depth, as measured by tailored evaluation metrics.
  arXiv  Detail & Related papers  (2025-05-29T17:32:15Z)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• How do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective [64.00022624183781]
  Large language models (LLMs) can assess relevance and support information retrieval (IR) tasks.<n>We investigate how different LLM modules contribute to relevance judgment through the lens of mechanistic interpretability.
  arXiv  Detail & Related papers  (2025-04-10T16:14:55Z)
• Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Ambiguous Prompts and Unanswerable Questions [60.31496362993982]
  Large language models (LLMs) frequently generate confident yet inaccurate responses.<n>We present a novel, test-time approach to detecting model hallucination through systematic analysis of information flow.
  arXiv  Detail & Related papers  (2024-12-13T16:14:49Z)
• Context is Key: A Benchmark for Forecasting with Essential Textual Information [87.3175915185287]
  "Context is Key" (CiK) is a forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context.<n>We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters.<n>We propose a simple yet effective LLM prompting method that outperforms all other tested methods on our benchmark.
  arXiv  Detail & Related papers  (2024-10-24T17:56:08Z)
• FinDABench: Benchmarking Financial Data Analysis Ability of Large Language Models [26.99936434072108]
  textttFinDABench is a benchmark designed to evaluate the financial data analysis capabilities of Large Language Models. textttFinDABench aims to provide a measure for in-depth analysis of LLM abilities.
  arXiv  Detail & Related papers  (2024-01-01T15:26:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.