# R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation Source: [R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation]() Collection index: [llms.txt]() Data updated: 2026-06-05T05:00:12.194Z Authors: Zhuohong Chen, Zhengxian Wu, Zirui Liao, Shenao Jiang, Hangrui Xu, Yang Chen, Chaokui Su, Xiaoyu Liu, Haoqian Wang Published: 2026-01-25T12:12:12.000Z ## Abstract Vision-centric retrieval for VQA requires retrieving images to supply missing visual cues and integrating them into the reasoning process. However, selecting the right images and integrating them effectively into the model's reasoning remains challenging.To address this challenge, we propose R3G, a modular Reasoning-Retrieval-Reranking framework.It first produces a brief reasoning plan that specifies the required visual cues, then adopts a two-stage strategy, with coarse retrieval followed by fine-grained reranking, to select evidence images.On MRAG-Bench, R3G improves accuracy across six MLLM backbones and nine sub-scenarios, achieving state-of-the-art overall performance. Ablations show that sufficiency-aware reranking and reasoning steps are complementary, helping the model both choose the right images and use them well. We release code and data at https://github.com/czh24/R3G. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Vision-centric Visual Question Answering on MRAG-Bench (test)](): Vision-centric Visual Question Answering; MRAG-Bench (test); Angle Robustness Score: 67.7. ## Original sources and implementation [Original paper]() [PDF]()