AI Paper Atlas

Research map / Video / Video-language understanding

Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation

Haichao Jiang, Tianming Liang, Wei-Shi Zheng, Jian-Fang Hu

CVPR 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 11 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 Existence Reflection (stage 1) (ablation)Refer-Agent · ReasonVOSJ&F: 66.6 -> 69.8Improved
add Consistency Reflection (stage 2) (ablation)Refer-Agent · ReasonVOSJ&F: 65.2 -> 69.8Improved
add both reflection stages (ablation)Refer-Agent · ReasonVOSJ&F: 64.5 -> 69.8Improved
use Dynamic Focus Layout instead of single keyframe (ablation)Refer-Agent · ReasonVOSJ&F: 67 -> 69.8Improved
use Dynamic Focus Layout instead of uniform frame integration (ablation)Refer-Agent · ReasonVOSJ&F: 67.7 -> 69.8Improved
increase MAX_TURN from 0 to 4 (ablation)Refer-Agent · ReasonVOSJ&F: 64.5 -> 69.8Improved
increase MAX_TURN from 4 to 6 (ablation)Refer-Agent · ReasonVOSJ&F: 69.8 -> 69.3No clear effect
keep separate agents instead of merging all tasks into one MLLM call (ablation)Refer-Agent · ReasonVOSJ&F: 62.5 -> 69.8Improved
swap Qwen2.5-VL-7B for Ovis2.5-9B as MLLM (ablation)Refer-Agent · ReasonVOSJ&F: 55.5 -> 69.8Improved
Refer-Agent (zero-shot) vs SFT RGA3 using same Qwen2.5-VL-7BRefer-Agent · ReasonVOSJ&F: 53.6 -> 55.5Improved
Refer-Agent vs SFT methods on GroundMoReRefer-Agent · GroundMoReJ&F: 27.2 -> 33.4Improved

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