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

2025-05-16 · Ayesha Amjad, Saurav Sthapit, Tahir Qasim Syed

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.

📄 PDF Abstract BibTeX arXiv:2505.13504

Code (1)

AyeshaAmjad0828/Unstructured-Data-Extraction paddle

Tasks

FormLanguage ModelingLanguage ModellingLarge Language ModelOptical Character Recognition (OCR)Reinforcement Learning (RL)

Verifiable Reinforcement Learning Systems via Compositionality

2023-09-09 · Cyrus Neary, Aryaman Singh Samyal, Christos Verginis, Murat Cubuktepe 외

We propose a framework for verifiable and compositional reinforcement learning (RL) in which a collection of RL subsystems, each of which learns to accomplish a separate subtask, are composed to achieve an overall task. …

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Verifiable and Compositional Reinforcement Learning Systems

2021-06-07 · Cyrus Neary, Christos Verginis, Murat Cubuktepe, Ufuk Topcu

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

TrafficClaw: A Generalizable LLM Agent in the Unified Physical Environment for Urban Traffic Control

2026-04-19 · Siqi Lai, Pan Zhang, Yuping Zhou, Jindong Han 외 arxiv

Large language model (LLM) agents have shown strong capabilities in long-horizon reasoning, tool use, and decision-making in digital environments, yet extending them to physically grounded systems remains challenging. Un…

Reinforcement Learning

DeepCAS: A Deep Reinforcement Learning Algorithm for Control-Aware Scheduling

2018-03-08 · Burak Demirel, Arunselvan Ramaswamy, Daniel E. Quevedo, Holger Karl

We consider networked control systems consisting of multiple independent controlled subsystems, operating over a shared communication network. Such systems are ubiquitous in cyber-physical systems, Internet of Things, an…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Agentic Design Patterns: A System-Theoretic Framework

2026-01-27 · Minh-Dung Dao, Quy Minh Le, Hoang Thanh Lam, Duc-Trong Le 외 arxiv

With the development of foundation model (FM), agentic AI systems are getting more attention, yet their inherent issues like hallucination and poor reasoning, coupled with the frequent ad-hoc nature of system design, lea…