Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA

Yuanlei Zheng, Pei Fu, Hang Li, Ziyang Wang +8 more

Published

Apr 15, 2026

Citations

0

Trust level

High

Usefulness score

65/100 (Medium)

Extraction confidence

80% (High)

Derived from extracted protocol signals and abstract evidence.

Rater population

Domain Experts

Signals refreshed

Aug 20, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics Demonstrations General

Should you rely on this paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Use this as a practical starting point for protocol research, then validate against the original paper.

Best use

Secondary protocol comparison source

Use if you need

A benchmark-and-metrics comparison anchor.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

No major weakness surfaced.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
65/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free methods face a trade-off between capacity and precision: end-to-end models scale poorly with document length, while visual retrieval-based pipelines are brittle and passive. We propose Doc-$V^*$, an \textbf{OCR-free agentic} framework that casts multi-page DocVQA as sequential evidence aggregation. Doc-$V^*$ begins with a thumbnail overview, then actively navigates via semantic retrieval and targeted page fetching, and aggregates evidence in a structured working memory for grounded reasoning. Trained by imitation learning from expert trajectories and further optimized with Group Relative Policy Optimization, Doc-$V^*$ balances answer accuracy with evidence-seeking efficiency. Across five benchmarks, Doc-$V^*$ outperforms open-source baselines and approaches proprietary models, improving out-of-domain performance by up to \textbf{47.9\%} over RAG baseline. Other results reveal effective evidence aggregation with selective attention, not increased input pages.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Demonstrations

Directly usable for protocol triage.

"Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents."

Benchmarks / Datasets

strong

DocVQA

Useful for quick benchmark comparison.

"We propose Doc-$V^*$, an \textbf{OCR-free agentic} framework that casts multi-page DocVQA as sequential evidence aggregation."

Reported Metrics

strong

Accuracy, Precision

Useful for evaluation criteria comparison.

"Existing OCR-free methods face a trade-off between capacity and precision: end-to-end models scale poorly with document length, while visual retrieval-based pipelines are brittle and passive."

Rater Population

strong

Domain Experts

Helpful for staffing comparability.

"Trained by imitation learning from expert trajectories and further optimized with Group Relative Policy Optimization, Doc-$V^*$ balances answer accuracy with evidence-seeking efficiency."

Benchmarks and datasets

DocVQA

Reported metrics

accuracyprecision
Human feedback details
Uses human feedback
Yes
Feedback types
Demonstrations
Rater population
Domain Experts
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
High
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents.
  • Existing OCR-free methods face a trade-off between capacity and precision: end-to-end models scale poorly with document length, while visual retrieval-based pipelines are brittle and passive.
  • We propose Doc-$V^*$, an \textbf{OCR-free agentic} framework that casts multi-page DocVQA as sequential evidence aggregation.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Expert verification evaluation Human demonstrations evaluation Accuracy

Contribution summary

  • We propose Doc-V^*, an OCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation.
  • Trained by imitation learning from expert trajectories and further optimized with Group Relative Policy Optimization, Doc-V^* balances answer accuracy with evidence-seeking efficiency.
  • Across five benchmarks, Doc-V^* outperforms open-source baselines and approaches proprietary models, improving out-of-domain performance by up to 47.9\% over RAG baseline.

Why it matters for eval

  • We propose Doc-V^*, an OCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation.
  • Across five benchmarks, Doc-V^* outperforms open-source baselines and approaches proprietary models, improving out-of-domain performance by up to 47.9\% over RAG baseline.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Demonstrations

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: DocVQA

  • Metric reporting is present

    Detected: accuracy, precision