# Wiki-R1: Incentivizing Multimodal Reasoning for Knowledge-based VQA via Data and Sampling Curriculum

arXiv: https://arxiv.org/abs/2603.05256 · HTML: https://mlsanity.com/paper/2603.05256/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 27 of its 63 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 27 of 27)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?](https://mlsanity.com/paper/2302.11713/) (2023)
- [Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions](https://mlsanity.com/paper/1901.01753/) (2019)
- [UniIR: Training and Benchmarking Universal Multimodal Information Retrievers](https://mlsanity.com/paper/2311.17136/) (2023)
- [KAT: A Knowledge Augmented Transformer for Vision-and-Language](https://mlsanity.com/paper/2112.08614/) (2021)
- [MMSearch-R1: Incentivizing LMMs to Search](https://mlsanity.com/paper/2506.20670/) (2025)
- [Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments](https://mlsanity.com/paper/1910.07224/) (2019)
- [Retrieval Augmented Visual Question Answering with Outside Knowledge](https://mlsanity.com/paper/2210.03809/) (2022)
- [Efficient Reinforcement Finetuning via Adaptive Curriculum Learning](https://mlsanity.com/paper/2504.05520/) (2025)
- [EchoSight: Advancing Visual-Language Models with Wiki Knowledge](https://mlsanity.com/paper/2407.12735/) (2024)
- [DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training](https://mlsanity.com/paper/2504.09710/) (2025)
- [VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning](https://mlsanity.com/paper/2507.22607/) (2025)
- [RoRA-VLM: Robust Retrieval-Augmented Vision Language Models](https://mlsanity.com/paper/2410.08876/) (2024)
- [A Simple Baseline for Knowledge-Based Visual Question Answering](https://mlsanity.com/paper/2310.13570/) (2023)
- [Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training](https://mlsanity.com/paper/2401.02347/) (2024)
- [Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generation](https://mlsanity.com/paper/2505.17391/) (2025)
- [DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM Hallucinations](https://mlsanity.com/paper/2601.00623/) (2026)
- [A Curriculum Learning Approach to Reinforcement Learning: Leveraging RAG for Multimodal Question Answering](https://mlsanity.com/paper/2508.10337/) (2025)
- [DACL-RAG: Data Augmentation Strategy with Curriculum Learning for Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.10493/) (2025)

## Built on by (most cited first, 2 of 2)

- [WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition](https://mlsanity.com/paper/2603.09921/) (2026)
- [UniHEAR: Unified Heterogeneous-Source Attentive Retrieval for Knowledge-Based Visual Question Answering](https://mlsanity.com/paper/2608.01147/) (2026)

## Abstract (arXiv)

Knowledge-Based Visual Question Answering (KB-VQA) requires models to answer questions about an image by integrating external knowledge, posing significant challenges due to noisy retrieval and the structured, encyclopedic nature of the knowledge base. These characteristics create a distributional gap from pretrained multimodal large language models (MLLMs), making effective reasoning and domain adaptation difficult in the post-training stage. In this work, we propose textitWiki-R1, a data-generation-based curriculum reinforcement learning framework that systematically incentivizes reasoning in MLLMs for KB-VQA. Wiki-R1 constructs a sequence of training distributions aligned with the model's evolving capability, bridging the gap from pretraining to the KB-VQA target distribution. We introduce textitcontrollable curriculum data generation, which manipulates the retriever to produce samples at desired difficulty levels, and a textitcurriculum sampling strategy that selects informative samples likely to yield non-zero advantages during RL updates. Sample difficulty is estimated using observed rewards and propagated to unobserved samples to guide learning. Experiments on two KB-VQA benchmarks, Encyclopedic VQA and InfoSeek, demonstrate that Wiki-R1 achieves new state-of-the-art results, improving accuracy from 35.5% to 37.1% on Encyclopedic VQA and from 40.1% to 44.1% on InfoSeek. The project page is available at https://artanic30.github.io/projectpages/WikiR1/.