Paper Citation Record · LEDGER

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

As of 9 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 16 inbound Pith citation observations for arXiv:2505.22019.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.22019 v2

Coverage vector

measured 54 of 54 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:24:54.668238Z

measured 70 of 70 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 16 of 16 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T13:23:34.984840Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-04T15:09:55.135392Z

Reference resolution

54 of 54 outbound references displayed

verified exact0
verified fuzzy8
unresolved46
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 69531200-78c5-409b-9075-705dee559482 · outbound

This paper cites write newline.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:48.648661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8ccdf16-eff3-4b06-8bc0-390b31df102e · outbound

This paper cites Qwen2.5-VL Technical Report.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Qwen2.5-VL Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:48.786792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 268315af-74ce-4a4d-8877-217f37f1bfc5 · outbound

This paper cites Benchmarking large language models in retrieval-augmented generation.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Benchmarking large language models in retrieval-augmented generation

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:24:56.946878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5baac46d-a7d7-4111-b649-57ccaf6cddc8 · outbound

This paper cites R1-v: Reinforcing super generalization ability in vision-language models with less than \ 3.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning R1-v: Reinforcing super generalization ability in vision-language models with less than \ 3

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:24:56.741210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cb69defb-b57e-41c1-bb83-ccf06e98986f · outbound

This paper cites ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:49.147441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0af78db5-411e-4aa0-afe7-7ceefecb0d9d · outbound

This paper cites Mindsearch: Mimicking human minds elicits deep ai searcher.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Mindsearch: Mimicking human minds elicits deep ai searcher

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:49.352425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 762efeb2-6d0c-4bec-97a0-d036d833bbeb · outbound

This paper cites Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:49.490774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9790918-9649-4cc5-ab71-331c48752194 · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:49.709222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d32f2860-0616-4982-b3a8-d69e8cd7924b · outbound

This paper cites M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:49.927205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8925cca-2976-4e05-b1cd-19f0c477861c · outbound

This paper cites PP-OCR: A Practical Ultra Lightweight OCR System.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning PP-OCR: A Practical Ultra Lightweight OCR System

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:50.065723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acb7fd87-8eb6-47a1-bd8b-4ed82d8b5d9e · outbound

This paper cites Colpali: Efficient document retrieval with vision language models.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Colpali: Efficient document retrieval with vision language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:24:56.538027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b48724e1-3d34-4973-8f85-220a4d7e13b9 · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:50.367366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07fc34a4-9d1a-4da1-a76d-6a940277e99b · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:50.460221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ff22933-ee18-42ad-9a6e-3307aa72aa7c · outbound

This paper cites Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:50.559672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00eeeb99-9d5a-4aeb-9c23-ed590f381a76 · outbound

This paper cites OpenAI o1 System Card.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning OpenAI o1 System Card

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:50.683709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00e16907-51c7-4867-a3b2-3f372a8b503a · outbound

This paper cites MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:50.840704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7548be0-6977-4d9b-8ed3-e540525ea30f · outbound

This paper cites DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:50.943846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0914aadd-44d0-486a-a3d4-d761414d506c · outbound

This paper cites Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:51.082163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ead5704-8345-4c87-852f-5f9e97d29a78 · outbound

This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:51.217474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e205582-82cd-4269-8724-f25b68dd7ad2 · outbound

This paper cites Reinforcement learning: A survey.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Reinforcement learning: A survey

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:24:56.351090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6d2d3ac9-3765-48a5-8255-04acfd34cbbf · outbound

This paper cites NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:51.601363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2d12a3a-869d-4955-84ef-bb3ddd92a9cb · outbound

This paper cites u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt \.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt \

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:51.700223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0219256-bd67-4df6-9a69-389dde6c5c69 · outbound

This paper cites Search-o1: Agentic Search-Enhanced Large Reasoning Models.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Search-o1: Agentic Search-Enhanced Large Reasoning Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:51.824122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11459a76-2481-48f2-b128-0ef82e496bae · outbound

This paper cites Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:51.884343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b9ceca8-29b6-4506-b59b-b18646e7e1e1 · outbound

This paper cites Towards General Text Embeddings with Multi-stage Contrastive Learning.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Towards General Text Embeddings with Multi-stage Contrastive Learning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:51.963166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8acbfd5-bd5a-4648-b7b9-5e14039ded2f · outbound

This paper cites Improved baselines with visual instruction tuning.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Improved baselines with visual instruction tuning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:52.036227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0f17fc1-8a65-485b-ae63-665bbe9a6844 · outbound

This paper cites LlamaIndex , 11 2022.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning LlamaIndex , 11 2022

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:52.146606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02dc48b8-0155-4e5a-a008-61cb42d6d12e · outbound

This paper cites Visual-RFT: Visual Reinforcement Fine-Tuning.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Visual-RFT: Visual Reinforcement Fine-Tuning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:52.248859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0ed3f2c-aa1f-435a-90bb-bee0c89944d7 · outbound

This paper cites MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:52.343132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d634e7bc-32f8-43f8-a76e-bec59d2d6849 · outbound

This paper cites MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:52.421805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c2ea2cf-8642-469e-924b-799c5c19984d · outbound

This paper cites Simpo: Simple preference optimization with a reference-free reward.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Simpo: Simple preference optimization with a reference-free reward

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:52.518896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c8c0d4e-b367-4663-93eb-1233a01ea3dd · outbound

This paper cites NV-Retriever: Improving text embedding models with effective hard-negative mining.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning NV-Retriever: Improving text embedding models with effective hard-negative mining

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:52.610720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dd90c39-b902-4ffc-b08b-f7206b3b0c2e · outbound

This paper cites Hello gpt-4o.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Hello gpt-4o

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:52.679894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcafe132-9e4f-4759-bc04-037d07ee81cb · outbound

This paper cites Introducing gemini 2.0: our new ai model for the agentic era, 2024.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Introducing gemini 2.0: our new ai model for the agentic era, 2024

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:52.763882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d251e266-f212-41fb-bcc0-cba2aec026cf · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Direct preference optimization: Your language model is secretly a reward model

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:52.861519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f33cf807-ebaa-485e-92ef-8f9286a003c8 · outbound

This paper cites Proximal Policy Optimization Algorithms.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Proximal Policy Optimization Algorithms

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:52.950386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65ebfb42-2e5d-49bc-9dfe-29506b85d40c · outbound

This paper cites Visual cot: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Visual cot: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:24:56.100544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d74a9cfd-9ee9-48f7-b84d-946c85862326 · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning HybridFlow: A Flexible and Efficient RLHF Framework

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:53.171877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b86812e1-643b-4b23-82d6-b42c127aa112 · outbound

This paper cites Reinforcement learning.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Reinforcement learning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:24:55.809640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ebfbe6e8-0a78-475e-9803-6fd86710633c · outbound

This paper cites Slidevqa: A dataset for document visual question answering on multiple images.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Slidevqa: A dataset for document visual question answering on multiple images

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:24:55.604920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 056425ae-5ace-4508-a89e-5f31bb5c7e35 · outbound

This paper cites ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:53.442043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ebaea24-4713-4d9a-a30b-d63e2cd79fc3 · outbound

This paper cites RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:53.487266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bd4bdc1-02f8-4d2f-98c2-88b1d53c7328 · outbound

This paper cites Simple statistical gradient-following algorithms for connectionist reinforcement learning.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Simple statistical gradient-following algorithms for connectionist reinforcement learning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:53.586633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f15666ee-bdbc-4691-9a14-5246d2f099a3 · outbound

This paper cites WebWalker: Benchmarking LLMs in Web Traversal.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning WebWalker: Benchmarking LLMs in Web Traversal

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:53.713826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e328ef64-c72b-47c8-8eda-6451b5932802 · outbound

This paper cites Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:53.810076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04b2de5d-2172-4ee4-baca-17c71b3a49fa · outbound

This paper cites Rule: Reliable multimodal rag for factuality in medical vision language models.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Rule: Reliable multimodal rag for factuality in medical vision language models

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:24:55.380239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3ec533b4-47bb-425c-bc96-4f0808b4965f · outbound

This paper cites Qwen2.5 Technical Report.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Qwen2.5 Technical Report

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:54.021458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 161fa363-a68a-42c3-8582-5de71460e329 · outbound

This paper cites React: Synergizing reasoning and acting in language models.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning React: Synergizing reasoning and acting in language models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:54.132125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 512576cf-8bdd-4828-88db-3d113f7ce37f · outbound

This paper cites Perception-R1: Pioneering Perception Policy with Reinforcement Learning.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Perception-R1: Pioneering Perception Policy with Reinforcement Learning

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:54.235680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59e799c9-745e-4f80-8775-79913f385c70 · outbound

This paper cites Introducing Visual Perception Token into Multimodal Large Language Model.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Introducing Visual Perception Token into Multimodal Large Language Model

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:54.345474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdcf5e24-caf3-41f1-8888-177af150b37d · outbound

This paper cites VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:54.427481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23622d0a-3561-49b8-9458-c3817c6b7f97 · outbound

This paper cites LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:54.491170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d0bfe84-fb56-4288-a145-74e854cc139d · outbound

This paper cites , " * write output.state after.block = add.period write.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning , " * write output.state after.block = add.period write

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:54.566124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d2679c0-1349-4812-9f51-95df8bf0e25d · outbound

This paper cites write newline.

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning write newline

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:54.668238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation e4dc91ff-51d2-4752-aa5a-47c8c4b80e89 · inbound

Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback cites this paper.

Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T13:23:34.984840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf6bdab8-5b24-4a69-9e98-363b25af0fbb · inbound

M2IO-R1: An Efficient RL-Enhanced Reasoning Framework for Multimodal Retrieval Augmented Multimodal Generation cites this paper.

M2IO-R1: An Efficient RL-Enhanced Reasoning Framework for Multimodal Retrieval Augmented Multimodal Generation VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T22:52:00.547279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a8a7c1b-2d4e-46f7-b0c4-35065cf68ee2 · inbound

DeepEyesV2: Toward Agentic Multimodal Model cites this paper.

DeepEyesV2: Toward Agentic Multimodal Model VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:32:29.448501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2967d069-f60e-4f57-8581-64b9eed36b05 · inbound

GeoBrowse: A Geolocation Benchmark for Agentic Tool Use with Expert-Annotated Reasoning Traces cites this paper.

GeoBrowse: A Geolocation Benchmark for Agentic Tool Use with Expert-Annotated Reasoning Traces VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Reference 47

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T17:33:02.362467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 97ad0c2a-e9dc-4d15-8928-993a8a37b856 · inbound

ReAlign: Optimizing the Visual Document Retriever with Reasoning-Guided Fine-Grained Alignment cites this paper.

ReAlign: Optimizing the Visual Document Retriever with Reasoning-Guided Fine-Grained Alignment VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Reference 85

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:58.159597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bec402f7-7a52-459e-b962-8d50ea8d82cf · inbound

VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning cites this paper.

VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:11:03.331597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 36ea29d2-7175-46ed-95d2-4625e83a559c · inbound

POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Management cites this paper.

POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Management VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Reference 45

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T13:10:26.498983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ca24bd0d-f4ba-4938-9eea-6f75e42bbbf8 · inbound

POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Management cites this paper.

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T16:18:24.497209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37e43759-ef2d-4700-bc61-27bd5aa2e355 · inbound

CC-OCR V2: Benchmarking Large Multimodal Models for Literacy in Real-world Document Processing cites this paper.

CC-OCR V2: Benchmarking Large Multimodal Models for Literacy in Real-world Document Processing VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Reference 62

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T23:46:49.213351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ce49c680-a71e-42ed-919f-fd2c54d9a638 · inbound

SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory cites this paper.

SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:13:40.493453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 39c126c9-dc8c-43cd-8c4d-2adf8647af8b · inbound

From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models cites this paper.

From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Reference 215

Resolution: verified exact; arxiv_id, observed 2026-07-04T15:09:55.136829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6ad6b6c6-2c8d-42bc-8c53-fde35b53ed31 · inbound

SimpleSearch-VL: A Simple Recipe for Multimodal Agentic Deep Search cites this paper.

SimpleSearch-VL: A Simple Recipe for Multimodal Agentic Deep Search VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T09:55:41.069237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c51fda0a-6a8b-47ae-ae27-03d8243df2b8 · inbound

BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception cites this paper.

BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Reference 163

Resolution: unresolved; no resolver link, observed 2026-07-12T04:17:40.198357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb841e23-0e1c-448e-9519-cdee7432d478 · inbound

Enhancing Large Multimodal Models in Key Information Extraction via Scene-Aware Document Synthesis cites this paper.

Enhancing Large Multimodal Models in Key Information Extraction via Scene-Aware Document Synthesis VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-11T16:02:00.920066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b77f11b1-eb43-4aaa-a7ba-0da6aa9f7156 · inbound

HierDoc: Hierarchical Page-to-Region Evidence Routing for Long-Document Visual Question Answering cites this paper.

HierDoc: Hierarchical Page-to-Region Evidence Routing for Long-Document Visual Question Answering VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-03T02:57:49.554753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07c32dab-92fe-471c-a56d-9a84f9aad946 · inbound

Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent cites this paper.

Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T04:44:27.203082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.