# Template-Based Financial Report Generation in Agentic and Decomposed Information Retrieval

arXiv: https://arxiv.org/abs/2504.14233 · HTML: https://mlsanity.com/paper/2504.14233/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 19 Apr 2025.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 16 of 16)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [An LLM Compiler for Parallel Function Calling](https://mlsanity.com/paper/2312.04511/) (2023)
- [ECTSum: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcripts](https://mlsanity.com/paper/2210.12467/) (2022)
- [Modeling financial analysts' decision making via the pragmatics and semantics of earnings calls](https://mlsanity.com/paper/1906.02868/) (2019)
- [An Exploratory Study of Stock Price Movements from Earnings Calls](https://mlsanity.com/paper/2203.12460/) (2022)
- [DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering](https://mlsanity.com/paper/2307.06869/) (2023)
- [From Facts to Insights: A Study on the Generation and Evaluation of Analytical Reports for Deciphering Earnings Calls](https://mlsanity.com/paper/2410.01039/) (2024)
- [Instruction-Guided Bullet Point Summarization of Long Financial Earnings Call Transcripts](https://mlsanity.com/paper/2405.06669/) (2024)
- [Efficient Aspect-Based Summarization of Climate Change Reports with Small Language Models](https://mlsanity.com/paper/2411.14272/) (2024)

## Built on by (most cited first, 8 of 8)

- [FinSight: Towards Real-World Financial Deep Research](https://mlsanity.com/paper/2510.16844/) (2025)
- [Quantifying Trust: Financial Risk Management for Trustworthy AI Agents](https://mlsanity.com/paper/2604.03976/) (2026)
- [FinDebate: Multi-Agent Collaborative Intelligence for Financial Analysis](https://mlsanity.com/paper/2509.17395/) (2025)
- [Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation](https://mlsanity.com/paper/2604.10741/) (2026)
- [VDAR-Router: Adaptive LLMs Routing via Verbalized Query Difficulty Analysis Retrieval](https://mlsanity.com/paper/2607.18098/) (2026)
- [CARPAS: Towards Content-Aware Refinement of Provided Aspects for Summarization in Large Language Models](https://mlsanity.com/paper/2510.07177/) (2025)
- [Enhancing Business Analytics through Hybrid Summarization of Financial Reports](https://mlsanity.com/paper/2601.09729/) (2025)
- [FollowTable: A Benchmark for Instruction-Following Table Retrieval](https://mlsanity.com/paper/2605.00400/) (2026)

## Abstract (arXiv)

Tailoring structured financial reports from companies' earnings releases is crucial for understanding financial performance and has been widely adopted in real-world analytics. However, existing summarization methods often generate broad, high-level summaries, which may lack the precision and detail required for financial reports that typically focus on specific, structured sections. While Large Language Models (LLMs) hold promise, generating reports adhering to predefined multi-section templates remains challenging. This paper investigates two LLM-based approaches popular in industry for generating templated financial reports: an agentic information retrieval (IR) framework and a decomposed IR approach, namely AgenticIR and DecomposedIR. The AgenticIR utilizes collaborative agents prompted with the full template. In contrast, the DecomposedIR approach applies a prompt chaining workflow to break down the template and reframe each section as a query answered by the LLM using the earnings release. To quantitatively assess the generated reports, we evaluated both methods in two scenarios: one using a financial dataset without direct human references, and another with a weather-domain dataset featuring expert-written reports. Experimental results show that while AgenticIR may excel in orchestrating tasks and generating concise reports through agent collaboration, DecomposedIR statistically significantly outperforms AgenticIR approach in providing broader and more detailed coverage in both scenarios, offering reflection on the utilization of the agentic framework in real-world applications.