AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

OCTOPUS: Multi‑Agentic Universal Compositional Visual Retrieval

Zhangtao Cheng, Bozhu Zheng, Ting Zhong, Fan Zhou

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 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
remove the creation agent (visual and textual proxies) (ablation)OCTOPUS · WebVid (ViT-L/14)avg Recall (R@1,R@5): 69.32 -> 76.21 (w/o Creator vs full)Improved
add retrieval verification (LLM re-ranking) (ablation)OCTOPUS · WebVid (ViT-L/14)avg Recall (R@1,R@5): 65.64 -> 76.21Improved
add self-refining tool in the Perceiver (ablation)OCTOPUS · WebVid (ViT-L/14)avg Recall (R@1,R@5): 70.57 -> 76.21Improved
add LLM reasoning (modification) tool in the Perceiver (ablation)OCTOPUS · WebVid (ViT-L/14)avg Recall (R@1,R@5): 70.68 -> 76.21Improved
add textual proxies (semantic increment) (ablation)OCTOPUS · CIRCO (ViT-L/14)avg mAP (k=5,10): 24.43 -> 28.42Improved
add visual proxy generation (ablation)OCTOPUS · WebVid (ViT-L/14)avg Recall (R@1,R@5): 71.45 -> 76.21Improved
use bidirectional retrieval instead of text-to-vision and vision-to-vision (ablation)OCTOPUS · WebVid (ViT-L/14)avg Recall (R@1,R@5): 71.49 -> 76.21Improved
swap GPT-4o-mini for open-source LLM MiniGPT-4 (ablation)OCTOPUS · WebVid (ViT-L/14)avg Recall (R@1,R@5): 76.21 -> 70.71Hurt
swap GPT-4o-mini for GPT-4o (ablation)OCTOPUS · WebVid and CIRCO (ViT-L/14)avg Recall / avg mAP: 76.21 -> 76.60; 28.42 -> 28.77No clear effect
increase visual-proxy weight lambda beyond optimum (ablation)OCTOPUS gating · WebVid, CIRCO, FashionIQ TopteeRecall / mAPHurt
add creator and retriever agents to LinCIR and OSrCIR (ablation)LinCIR, OSrCIR · WebVidRecall@kImproved
use OCTOPUS vs supervised/zero-shot baselines on FashionIQOCTOPUS · FashionIQ ViT-L/14avg Recall@10: 33.26 -> 37.00Improved

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