AI Paper Atlas

Research map / Video / Video-language understanding

A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoning

Yichang Xu, Gaowen Liu, Ramana Rao Kompella, Tiansheng Huang, Sihao Hu, Fatih Ilhan, Selim Furkan Tekin, Zachary Yahn, Ling Liu

CVPR 2026 · Video › Video-language understanding · approach: Video question answering · 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
sample perception frames randomly instead of per event block (ablation)A4VL · EgoSchema (test, 500 QA)accuracy: 79.6 -> 82.2Improved
use event-based blocks instead of uniform blocks for action frames (ablation)A4VL · EgoSchema (test, 500 QA)accuracy: 80.2 -> 82.2Improved
require full consensus instead of majority consensus (ablation)A4VL · EgoSchema (test, 500 QA)accuracy: 81.4 -> 82.2Improved
require full consensus instead of majority consensus (ablation)A4VL · EgoSchema (test, 500 QA) latencyseconds per sample: 26s -> 37sHurt
add agent pruning (vs sum selection) (ablation)A4VL · EgoSchema (test, 500 QA)accuracy: 80.8 -> 82.2Improved
add agent pruning (vs majority selection) (ablation)A4VL · EgoSchema (test, 500 QA)accuracy: 79.4 -> 82.2Improved
add agent pruning (ablation)A4VL · EgoSchema (test, 500 QA) latencyseconds per sample: 60s -> 37sImproved
allow more collaboration rounds (ablation)A4VL · all five benchmarksaccuracyImproved
replace single strong MLLM with A4VL multi-agent frameworkInternVL3-78B · EgoSchema (test, 500 QA)accuracy: 76.8 -> 82.2Improved
use A4VL instead of GPT-4o on MLVUGPT-4o · MLVU latencyseconds per sample: 127s -> 74sImproved
use A4VL instead of GPT-4oGPT-4o · LongVideoBenchaccuracy: 66.7 -> 72.2Improved

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