SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.12735 · 2026

VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph

Lin Chen, Pengjun Xie, Qiang Zhang, Wenxuan Huang, Shihang Wang, Ruixue Ding, Zehui Chen, Qiuchen Wang, Yu Zeng, Zhuoning Guo, Fanrui Zhang, Bosi Zhang

arXiv · PDF · Open in the Atlas

Code that ran

8 of 14 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 6 failures of our instrument; 6 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.12735.json · badge: /api/ran/2602.12735.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Alibaba-NLP/VRAG canonical (classifier label)
classifier basis: census
8 ran · 6 no recorded run
FunctionStatusWhere it lives
convert_to_regular_types Ran
ran; our contract draft was wrong, not the code
Alibaba-NLP/VRAG/VRAG-RL/verl/trainer/fsdp_sft_trainer.py
pointer only (licence: NONE) · get_code("f887d72c9492d9ee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Alibaba-NLP/VRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_step Ran
ran, honoured the contract we drafted
Alibaba-NLP/VRAG/VRAG-RL/verl/trainer/fsdp_sft_trainer.py
pointer only (licence: NONE) · get_code("216e28c040173a61")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Alibaba-NLP/VRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_huggingface_actor_config Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Alibaba-NLP/VRAG/VRAG-RL/verl/utils/model.py
pointer only (licence: NONE) · get_code("fe79c459a3e4cc64")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Alibaba-NLP/VRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_rope_index Ran
ran; our contract draft was wrong, not the code
Alibaba-NLP/VRAG/VRAG-RL/verl/models/transformers/qwen2_vl.py
pointer only (licence: NONE) · get_code("e29ba2dcd05add9f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Alibaba-NLP/VRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

is_transformers_version_in_range Ran
ran, violated the contract we drafted
Alibaba-NLP/VRAG/VRAG-RL/verl/models/transformers/monkey_patch.py
pointer only (licence: NONE) · get_code("42a7954a8cfa89e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Alibaba-NLP/VRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

prepare_fa2_from_position_ids Ran
ran; our contract draft was wrong, not the code
Alibaba-NLP/VRAG/VRAG-RL/verl/models/transformers/qwen2_vl.py
pointer only (licence: NONE) · get_code("e89bd73550a8c08f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Alibaba-NLP/VRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

process_image Ran
ran; our contract draft was wrong, not the code
Alibaba-NLP/VRAG/VRAG-RL/vrag_agent/generation.py
pointer only (licence: NONE) · get_code("a4157e7f60cde433")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Alibaba-NLP/VRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

unpad_dataproto Ran
ran; our contract draft was wrong, not the code
Alibaba-NLP/VRAG/VRAG-RL/verl/protocol.py
pointer only (licence: NONE) · get_code("25f0ea3f460f6ce1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Alibaba-NLP/VRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_monkey_patch Not yet run
unverified (harvested, no recorded run)
Alibaba-NLP/VRAG/VRAG-RL/verl/models/transformers/monkey_patch.py
pointer only (licence: NONE) · get_code("63fac81eb8667d39")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Alibaba-NLP/VRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

flash_attention_forward Not yet run
unverified (harvested, no recorded run)
Alibaba-NLP/VRAG/VRAG-RL/verl/models/transformers/qwen2_vl.py
pointer only (licence: NONE) · get_code("736144d442549c26")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Alibaba-NLP/VRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_generation_config Not yet run
unverified (harvested, no recorded run)
Alibaba-NLP/VRAG/VRAG-RL/verl/utils/model.py
pointer only (licence: NONE) · get_code("660713a8fa047736")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Alibaba-NLP/VRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_weight_loader Not yet run
unverified (harvested, no recorded run)
Alibaba-NLP/VRAG/VRAG-RL/verl/models/weight_loader_registry.py
pointer only (licence: NONE); the stored copy get_code serves, from ncbi-nlp/Med-V1, is pointer only (licence: NOASSERTION) · get_code("af005d03c2088909")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Alibaba-NLP/VRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_weight_saver Not yet run
unverified (harvested, no recorded run)
Alibaba-NLP/VRAG/VRAG-RL/verl/models/weight_loader_registry.py
pointer only (licence: NONE) · get_code("914227ac881d05be")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Alibaba-NLP/VRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

squeeze Not yet run
unverified (harvested, no recorded run)
Alibaba-NLP/VRAG/VRAG-RL/verl/utils/model.py
pointer only (licence: NONE) · get_code("3b15e2ac7497c441")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Alibaba-NLP/VRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 13 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 6 the same month, 7 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
unpad_dataproto 89 other papers
36 dated earlier, 13 the same month, 37 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
and 86 more not named here
squeeze 82 other papers
36 dated earlier, 12 the same month, 31 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
and 79 more not named here
get_generation_config 63 other papers
22 dated earlier, 10 the same month, 29 later, 2 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2502.19613 (2025-02)
Self-rewarding correction for mathematical reasoning
and 60 more not named here
get_huggingface_actor_config 53 other papers
34 dated earlier, 5 the same month, 12 later, 2 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
and 50 more not named here
extract_step 19 other papers
13 dated earlier, 3 the same month, 2 later, 1 undated
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
2502.14768 (2025-02)
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
and 16 more not named here
is_transformers_version_in_range 14 other papers
11 dated earlier, 2 later, 1 undated
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
2502.14768 (2025-02)
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
and 11 more not named here
convert_to_regular_types 7 other papers
5 dated earlier, 2 the same month
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2504.05520 (2025-04)
Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
2505.04588 (2025-05)
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
and 4 more not named here
get_weight_loader 4 other papers
3 dated earlier, 1 later
2502.19613 (2025-02)
Self-rewarding correction for mathematical reasoning
2505.18822 (2025-05)
AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting
2505.24875 (2025-05)
ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL
and 1 more not named here
apply_monkey_patch 2 other papers
2 dated earlier
2502.19613 (2025-02)
Self-rewarding correction for mathematical reasoning
2505.18917 (2025-05)
Behavior Injection: Preparing Language Models for Reinforcement Learning
flash_attention_forward 2 other papers
2 dated earlier
2502.19613 (2025-02)
Self-rewarding correction for mathematical reasoning
2504.05520 (2025-04)
Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
get_rope_index 2 other papers
2 dated earlier
2502.19613 (2025-02)
Self-rewarding correction for mathematical reasoning
2504.05520 (2025-04)
Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
get_weight_saver 2 other papers
2 dated earlier
2502.19613 (2025-02)
Self-rewarding correction for mathematical reasoning
2505.18822 (2025-05)
AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting
prepare_fa2_from_position_ids 2 other papers
2 dated earlier
2502.19613 (2025-02)
Self-rewarding correction for mathematical reasoning
2504.05520 (2025-04)
Efficient Reinforcement Finetuning via Adaptive Curriculum Learning

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Effectively retrieving, reasoning, and understanding multimodal information remains a critical challenge for agentic systems. Traditional Retrieval-augmented Generation (RAG) methods rely on linear interaction histories, which struggle to handle longcontext tasks, especially those involving information-sparse yet token-heavy visual data in iterative reasoning scenarios. To bridge this gap, we introduce VimRAG, a framework tailored for multimodal Retrieval-augmented Reasoning across text, images, and videos. Inspired by our systematic study, we model the reasoning process as a dynamic directed acyclic graph that structures the agent states and retrieved multimodal evidence. Building upon this structured memory, we introduce a Graph-Modulated Visual Memory Encoding mechanism, with which the significance of memory nodes is evaluated via their topological position, allowing the model to dynamically allocate high-resolution tokens to pivotal evidence while compressing or discarding trivial clues. To implement this paradigm, we propose a Graph-Guided Policy Optimization strategy. This strategy disentangles step-wise validity from trajectory-level rewards by pruning memory nodes associated with redundant actions, thereby facilitating fine-grained credit assignment. Extensive experiments demonstrate that VimRAG consistently achieves state-of-the-art performance on diverse multimodal RAG benchmarks. The code is available at https://github.com/Alibaba-NLP/VRAG.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.12735")
get_code_for_paper("2602.12735")
have("2602.12735")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.12735.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.12735.svg)](https://syntology.ai/paper/2602.12735)

Connect an agent — have() is free.