# Agentic Retrieval for Financial Documents (AI Grand Challenge on FinAgentBench)

> We provide all participants with a baseline guide [HERE](https://www.kaggle.com/code/jihoonkwon/baseline-for-agentic-retrieval-grand-challenge).
> As we show in the demo, even simple changes like swapping in different LLMs or adjusting prompting could lead to clear improvements. You do not need deep LLM expertise to participate.

The **AI Agentic Retrieval Grand Challenge at ICAIF ’25** is motivated by the need for financial AI systems that can move beyond what traditional methods can achieve in accuracy to deliver interpretable, evidence-grounded answers from complex SEC filings. Participants are tasked with **building retrieval systems** by ***optimizing a system prompt*** that can support complex institutional finance questions with character-level evidence attribution. This competition is built on **FinAgentBench**, a benchmark purpose-built to evaluate **multi-step, agentic retrieval**.
Each query requires reasoning across **two stages**: first, *selecting the most relevant document type* (Document-Level Ranking), and second, *identifying the most relevant passages within single document* (Chunk-Level Ranking). The dataset contains about 26K examples curated by expert financial analysts from real SEC filings (2023–2024). Participants must return ranked results for both **document-level and chunk-level ranking tasks**.

## Participants who impress with their solutions (and explain how they achieved them) will be invited as a presenter sharing their work at ICAIF ’25. 
Further details will be announced once sponsorship is confirmed.