Skip to content
← Back to explorer

AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation

Zhengren Wang, Dongsheng Ma, Huaping Zhong, Jiayu Li, Wentao Zhang, Bin Wang, Conghui He · Feb 27, 2026 · Citations: 0

Automatic Metrics
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Feb 27, 2026, 4:09 PM

Recent

Extraction refreshed

Mar 8, 2026, 3:37 AM

Fresh

Extraction source

Runtime deterministic fallback

Confidence 0.35

Abstract

The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, such as financial reports. While page-level chunking and retrieval is a natural starting point, it creates a critical bottleneck: delivering entire pages to the generator introduces excessive extraneous context. This not only overloads the generator's attention mechanism but also dilutes the most salient evidence. Moreover, compressing these information-rich pages into a limited visual token budget further increases the risk of hallucinations. To address this, we introduce AgenticOCR, a dynamic parsing paradigm that transforms optical character recognition (OCR) from a static, full-text process into a query-driven, on-demand extraction system. By autonomously analyzing document layout in a "thinking with images" manner, AgenticOCR identifies and selectively recognizes regions of interest. This approach performs on-demand decompression of visual tokens precisely where needed, effectively decoupling retrieval granularity from rigid page-level chunking. AgenticOCR has the potential to serve as the "third building block" of the visual document RAG stack, operating alongside and enhancing standard Embedding and Reranking modules. Experimental results demonstrate that AgenticOCR improves both the efficiency and accuracy of visual RAG systems, achieving expert-level performance in long document understanding. Code and models are available at https://github.com/OpenDataLab/AgenticOCR.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.35 (below strong-reference threshold).
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Runtime deterministic fallback missing

No explicit feedback protocol extracted.

Evidence snippet: The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, such as financial reports.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Runtime deterministic fallback evidenced

Includes extracted eval setup.

Evidence snippet: The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, such as financial reports.

Quality Controls

missing

Not reported

Confidence: Low Source: Runtime deterministic fallback missing

No explicit QC controls found.

Evidence snippet: The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, such as financial reports.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Runtime deterministic fallback missing

No benchmark anchors detected.

Evidence snippet: The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, such as financial reports.

Reported Metrics

partial

Accuracy

Confidence: Low Source: Runtime deterministic fallback evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Experimental results demonstrate that AgenticOCR improves both the efficiency and accuracy of visual RAG systems, achieving expert-level performance in long document understanding.

Rater Population

partial

Domain Experts

Confidence: Low Source: Runtime deterministic fallback evidenced

Helpful for staffing comparability.

Evidence snippet: Experimental results demonstrate that AgenticOCR improves both the efficiency and accuracy of visual RAG systems, achieving expert-level performance in long document understanding.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Domain Experts
  • Unit of annotation: Ranking
  • Expertise required: Coding
  • Extraction source: Runtime deterministic fallback

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.35
  • Flags: low_signal, possible_false_positive, runtime_fallback_extraction

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

accuracy

Research Brief

Deterministic synthesis

To address this, we introduce AgenticOCR, a dynamic parsing paradigm that transforms optical character recognition (OCR) from a static, full-text process into a query-driven, on-demand extraction system. HFEPX signals include Automatic Metrics with confidence 0.35. Updated from current HFEPX corpus.

Generated Mar 8, 2026, 3:37 AM · Grounded in abstract + metadata only

Key Takeaways

  • To address this, we introduce AgenticOCR, a dynamic parsing paradigm that transforms optical character recognition (OCR) from a static, full-text process into a query-driven,…
  • By autonomously analyzing document layout in a "thinking with images" manner, AgenticOCR identifies and selectively recognizes regions of interest.

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Validate metric comparability (accuracy).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Low-signal flag detected: protocol relevance may be indirect.

Research Summary

Contribution Summary

  • To address this, we introduce AgenticOCR, a dynamic parsing paradigm that transforms optical character recognition (OCR) from a static, full-text process into a query-driven, on-demand extraction system.
  • By autonomously analyzing document layout in a "thinking with images" manner, AgenticOCR identifies and selectively recognizes regions of interest.
  • Experimental results demonstrate that AgenticOCR improves both the efficiency and accuracy of visual RAG systems, achieving expert-level performance in long document understanding.

Why It Matters For Eval

  • To address this, we introduce AgenticOCR, a dynamic parsing paradigm that transforms optical character recognition (OCR) from a static, full-text process into a query-driven, on-demand extraction system.
  • Experimental results demonstrate that AgenticOCR improves both the efficiency and accuracy of visual RAG systems, achieving expert-level performance in long document understanding.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: accuracy

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote