Papers › SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and...

SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement

16 Jun 2025arXiv:2506.14035archive 2025-07-28

Chelsi Jain, Yiran Wu, Yifan Zeng, Jiale Liu, S hengyu Dai, Zhenwen Shao, Qingyun Wu, Huazheng Wang

Document Visual Question Answering (DocVQA) is a practical yet challenging task, which is to ask questions based on documents while referring to multiple pages and different modalities of information, e.g, images and tables. To handle multi-modality, recent methods follow a similar Retrieval Augmented Generation (RAG) pipeline, but utilize Visual Language Models (VLMs) based embedding model to embed and retrieve relevant pages as images, and generate answers with VLMs that can accept an image as input. In this paper, we introduce SimpleDoc, a lightweight yet powerful retrieval - augmented framework for DocVQA. It boosts evidence page gathering by first retrieving candidates through embedding similarity and then filtering and re-ranking these candidates based on page summaries. A single VLM-based reasoner agent repeatedly invokes this dual-cue retriever, iteratively pulling fresh pages into a working memory until the question is confidently answered. SimpleDoc outperforms previous baselines by 3.2% on average on 4 DocVQA datasets with much fewer pages retrieved. Our code is available at https://github.com/ag2ai/SimpleDoc.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2506.14035")

Code

Syntology Ran 0 of 11 code samples harvested from 1 repository linked to this paper; 11 have no recorded run.

By repository: official repository: 11 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ag2ai/simpledoc officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested; 0 ran; 0 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

11unverified

Licence: 11 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ag2ai/SimpleDoc. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

calculate_metrics ag2ai/SimpleDoc/evaluation/analyze_multiple_runs.py official repository unverified no licence file found · pointer only · 36d783e0916c23cb · report
evaluate_response ag2ai/SimpleDoc/evaluation/evaluate_responses.py official repository unverified no licence file found · pointer only · d41c5a9581a7862d · report
extract_document_summary ag2ai/SimpleDoc/modules/step02_page_retrieval.py official repository unverified no licence file found · pointer only · 442a4d51b3fdf933 · report
extract_relevant_pages ag2ai/SimpleDoc/modules/step02_page_retrieval.py official repository unverified no licence file found · pointer only · dcb682866c231e85 · report
is_ground_truth_not_answerable ag2ai/SimpleDoc/evaluation/evaluate_pipeline.py official repository unverified no licence file found · pointer only · 0017500466774ab3 · report
load_eval_results ag2ai/SimpleDoc/evaluation/analyze_multiple_runs.py official repository unverified no licence file found · pointer only · 318f11f47eb00c0c · report
load_ground_truth ag2ai/SimpleDoc/evaluation/evaluate_responses.py official repository unverified no licence file found · pointer only · a60837f27b20ddec · report
load_results ag2ai/SimpleDoc/evaluation/evaluate_responses.py official repository unverified no licence file found · pointer only · d96da92d8a935925 · report
postprocess_answer ag2ai/SimpleDoc/modules/step03_target_page_qa.py official repository unverified no licence file found · pointer only · e9fd0d235482a280 · report
query_llm_for_page_retrieval ag2ai/SimpleDoc/modules/step02_page_retrieval.py official repository unverified no licence file found · pointer only · b75b739aeeeb160e · report
query_llm_with_images ag2ai/SimpleDoc/modules/step03_target_page_qa.py official repository unverified no licence file found · pointer only · b95b72231eb3aa73 · report

Tasks

Question AnsweringRAGRe-RankingRetrievalRetrieval-augmented GenerationVisual Question Answeringdocument understanding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections