AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories

Chenlong Deng, Mengjie Deng, Junjie Wu, Dun Zeng, Teng Wang, Qingsong Xie, Jiadeng Huang, Shengjie Ma, Changwang Zhang, Zhaoxiang Wang, Jun Wang, Yutao Zhu and 1 more

ICML 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Composed and text-based image retrieval · 0 citations (OpenAlex)

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 GetMetadata tool (ablation)ImageSeeker (Gemini-3-Flash-Preview) · DISBenchF1 (overall): 31.1 -> 36.8Improved
add FilterMetadata tool (ablation)ImageSeeker (Gemini-3-Flash-Preview) · DISBenchF1 (overall): 31.8 -> 36.8Improved
add ViewPhotos tool (ablation)ImageSeeker (Gemini-3-Flash-Preview) · DISBenchF1 (overall): 32.9 -> 36.8Improved
add WebSearch tool (ablation)ImageSeeker (Gemini-3-Flash-Preview) · DISBenchF1 (overall): 32.2 -> 36.8Improved
add explicit state memory (ablation)ImageSeeker (Gemini-3-Flash-Preview) · DISBenchF1 (overall): 31.9 -> 36.8Improved
add memory compression (ablation)ImageSeeker (Gemini-3-Flash-Preview) · DISBenchF1 (overall): 33.9 -> 36.8Improved
add explicit state memory (ablation)ImageSeeker (Gemini-3-Flash-Preview) · DISBenchF1 (inter-event): intra 34.1 -> 42.4; inter 30.1 -> 31.9Improved
increase parallel instances N with Best@k selectionImageSeeker (Gemini-3-Flash-Preview) · DISBenchF1: 35.4 -> 60.8Improved
increase parallel instances N with Majority VotingImageSeeker (Gemini-3-Flash-Preview) · DISBenchF1Improved
switch embedding model from 2B to 8BImageSeeker agents · DISBenchF1 (overall): Claude-Sonnet-4.5 39.4 -> 43.8; GPT-5.2 35.1 -> 30.0Mixed

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