paper-with-me

홈 › Papers

ARIAL: An Agentic Framework for Document VQA with Precise Answer Localization

2025-11-22 · Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Dheeraj Kulshrestha, Rajiv Ramnath arxiv

Document Visual Question Answering (VQA) requires models to not only extract accurate textual answers but also precisely localize them within document images, a capability critical for interpretability in high-stakes applications. However, existing systems achieve strong textual accuracy while producing unreliable spatial grounding, or sacrifice performance for interpretability. We present ARIAL (Agentic Reasoning for Interpretable Answer Localization), a modular framework that orchestrates specialized tools through an LLM-based planning agent to achieve both precise answer extraction and reliable spatial grounding. ARIAL decomposes Document VQA into structured subtasks: OCR-based text extraction with TrOCR, retrieval-augmented context selection using semantic search, answer generation via a fine-tuned Gemma 3-27B model, and explicit bounding-box localization through text-to-region alignment. This modular architecture produces transparent reasoning traces, enabling tool-level auditability and independent component optimization. We evaluate ARIAL on four benchmarks (DocVQA, FUNSD, CORD, and SROIE) using both textual accuracy (ANLS) and spatial precision (mAP at IoU 0.50 to 0.95). ARIAL achieves state-of-the-art results across all datasets: 88.7 ANLS and 50.1 mAP on DocVQA, 90.0 ANLS and 50.3 mAP on FUNSD, 85.5 ANLS and 60.2 mAP on CORD, and 93.1 ANLS on SROIE, surpassing the previous best method (DLaVA) by +2.8 ANLS and +3.9 mAP on DocVQA. Our work demonstrates how agentic orchestration of specialized tools can simultaneously improve performance and interpretability, providing a pathway toward trustworthy, explainable document AI systems.

📄 PDF Abstract BibTeX arXiv:2511.18192

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Question AnsweringAnswer GenerationDocument AI

Results from the Paper

RankTaskDatasetModelMetrics
#2 Visual Question Answering (VQA) DocVQA ARIAL ANLS: 50.1

Similar Papers 제목 키워드 기반

Learning to Summarize by Learning to Quiz: Adversarial Agentic Collaboration for Long Document Summarization

2025-09-25 · Weixuan Wang, Minghao Wu, Barry Haddow, Alexandra Birch arxiv

Long document summarization remains a significant challenge for current large language models (LLMs), as existing approaches commonly struggle with information loss, factual inconsistencies, and coherence issues when pro…

Document Summarization

Knowledge Graph RAG: Agentic Crawling and Graph Construction in Enterprise Documents

2026-04-14 · Koushik Chakraborty, Koyel Guha arxiv

This research paper addresses the limitations of semantic search in complex enterprise document ecosystems. Traditional RAG pipelines often fail to capture hierarchical and interconnected information, leading to retrieva…

Knowledge Graphs

FinanceComplexQA: Benchmarking Agentic Reasoning on Industrial-grade Financial Documents

2026-07-21 · Xianfu Cheng, Shiwei Zhang, Jiyu Zhao, Jian Yang 외 hf

Agentic Reasoning has become a transformative force in financial analysis due to its ability to integrate large-scale information and generate reliable and accurate content. However, when handling complex real-world prob…

Toward Agentic RAG for Ukrainian

2026-04-16 · Marta Sumyk, Oleksandr Kosovan arxiv

We present an initial investigation into Agentic Retrieval-Augmented Generation (RAG) for Ukrainian, conducted within the UNLP 2026 Shared Task on Multi-Domain Document Understanding. Our system combines two-stage retrie…

DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering

2026-03-12 · Teng Lin, Yizhang Zhu, Zhengxuan Zhang, Yuyu Luo 외 arxiv

Multi-document Multi-entity Question Answering inherently demands models to track implicit logic between multiple entities across scattered documents. However, existing Large Language Models (LLMs) and Retrieval-Augmente…

Information ExtractionRelational ReasoningQuestion Answering