# An agentic system with reinforcement-learned subsystem improvements for parsing form-like documents

arXiv: https://arxiv.org/abs/2505.13504 · HTML: https://mlsanity.com/paper/2505.13504/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 16 May 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 17 of 17)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding](https://mlsanity.com/paper/2202.13669/) (2022)
- [BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents](https://mlsanity.com/paper/2108.04539/) (2021)
- [Chargrid: Towards Understanding 2D Documents](https://mlsanity.com/paper/1809.08799/) (2018)
- [XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding](https://mlsanity.com/paper/2203.06947/) (2022)
- [MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration](https://mlsanity.com/paper/2311.08562/) (2023)
- [GenIE: Generative Information Extraction](https://mlsanity.com/paper/2112.08340/) (2021)
- [Instruct and Extract: Instruction Tuning for On-Demand Information Extraction](https://mlsanity.com/paper/2310.16040/) (2023)
- [CloudScan - A configuration-free invoice analysis system using recurrent neural networks](https://mlsanity.com/paper/1708.07403/) (2017)
- [FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction](https://mlsanity.com/paper/2305.02549/) (2023)
- [A Question-Answering Approach to Key Value Pair Extraction from Form-like Document Images](https://mlsanity.com/paper/2304.07957/) (2023)
- [GenKIE: Robust Generative Multimodal Document Key Information Extraction](https://mlsanity.com/paper/2310.16131/) (2023)
- [Graph Neural Networks and Representation Embedding for Table Extraction in PDF Documents](https://mlsanity.com/paper/2208.11203/) (2022)

## Built on by (most cited first, 1 of 1)

- [POLARIS: Typed Planning and Governed Execution for Agentic AI in Back-Office Automation](https://mlsanity.com/paper/2601.11816/) (2026)

## Abstract (arXiv)

Extracting alphanumeric data from form-like documents such as invoices, purchase orders, bills, and financial documents is often performed via vision (OCR) and learning algorithms or monolithic pipelines with limited potential for systemic improvements. We propose an agentic AI system that leverages Large Language Model (LLM) agents and a reinforcement learning (RL) driver agent to automate consistent, self-improving extraction under LLM inference uncertainty. Our work highlights the limitations of monolithic LLM-based extraction and introduces a modular, multi-agent framework with task-specific prompts and an RL policy of rewards and penalties to guide a meta-prompting agent to learn from past errors and improve prompt-based actor agents. This self-corrective adaptive system handles diverse documents, file formats, layouts, and LLMs, aiming to automate accurate information extraction without the need for human intervention. Results as reported on two benchmark datasets of SOIRE, and CORD, are promising for the agentic AI framework.