AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

MMAgent-R2: Learning to Rerank and Reject for Agentic mRAG

Tao Zhang, Ziqi Zhang, Zongyang Ma, Yuxin Yang, Bing Li, Chunfeng Yuan, Kang Rong, Fengyun Rao, Jing LYU, Weiming Hu

ECCV 2026 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add visual reranking (ablation)MMAgent-R2-8B · InfoSeek (26K train)accuracy (All): 40.2 -> 44.3Improved
add active rejection on top of reranking (ablation)MMAgent-R2-8B · InfoSeek (26K train)accuracy (All): 44.3 -> 45.5Improved
increase candidate batch size K from 3 to 5 (ablation)MMAgent-R2-8B · InfoSeek (26K train)accuracy (All): 44.7 -> 45.5Improved
increase candidate batch size K from 5 to 7 (ablation)MMAgent-R2-8B · InfoSeek (26K train)accuracy (All): 45.5 -> 45.7No clear effect
increase max rejection count from 0 to 2 (ablation)MMAgent-R2-8B · InfoSeek (26K train)accuracy (All): 44.3 -> 45.5Improved
increase max rejection count from 2 to 3 (ablation)MMAgent-R2-8B · InfoSeek (26K train)accuracy (All): 45.5 -> 44.8Hurt
increase rejection reward delta from 0.1 to 0.2 (ablation)MMAgent-R2-8B · InfoSeek (26K train)accuracy (All): 44.9 -> 45.5Improved
increase rejection reward delta from 0.2 to 0.3 (ablation)MMAgent-R2-8B · InfoSeek (26K train)accuracy (All): 45.5 -> 45.2Hurt
add visual reranking and rejection to retriever top-1MMAgent-R2-8B · E-VQAentity identification accuracy: 15.4 -> 29.5Improved
use MMAgent-R2 instead of MMhops-R1 (no visual verification)agentic mRAG · InfoSeek allaccuracy: 33.2 -> 50.2Improved
use MMAgent-R2-8B vs ReAGmRAG · E-VQA allaccuracy: 47.0 -> 54.2Improved
use MMAgent-R2-8B vs Gemini-2.5-Promulti-hop VQA · MMhops Comparisonaccuracy: 29.4 -> 39.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy