AI Paper Atlas

Research map / Video / Video-language understanding

LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents

Boyu Chen, Zhengrong Yue, Siran Chen, Zikang Wang, Yang Liu, Peng Li, Yali Wang

ICCV 2025 · Video › Video-language understanding · approach: Long video understanding · 58 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 Perception retrieval (ablation)LVAgent without Reflection · LongVideoBenchaccuracy: 63.9 -> 69.0Improved
add Reflection (ablation)LVAgent without Perception · LongVideoBenchaccuracy: 63.9 -> 72.2Improved
add both Perception and Reflection (ablation)LVAgent baseline (global 128 frames) · LongVideoBenchaccuracy: 63.9 -> 80.0Improved
add both Perception and Reflection (ablation)LVAgent baseline (global 128 frames) · VideoMME (w/o subs)accuracy: 72.1 -> 81.7Improved
combine three agents instead of one (ablation)LVAgent, round 1 · LongVideoBenchaccuracy: 68.3 -> 69.0Improved
increase collaboration rounds from 1 to 3 (ablation)LVAgent · LongVideoBenchaccuracy: 69.0 -> 80.0Improved
increase collaboration rounds from 1 to 3 (ablation)LVAgent · MLVUaccuracy: 79.2 -> 83.9Improved
use fine-tuned ASP-CLIP instead of CLIP (ablation)LVAgent retriever · LongVideoBenchaccuracy: 74.7 -> 80.0Improved
use fine-tuned ASP-CLIP instead of LongCLIP (ablation)LVAgent retriever · LongVideoBenchaccuracy: 75.6 -> 80.0Improved
use dynamic collaboration instead of Best Score (ablation)LVAgent discussion · LongVideoBenchaccuracy: 76.9 -> 80.0Improved
use dynamic collaboration instead of Decide by Agent (ablation)LVAgent discussion · MLVUaccuracy: 79.9 -> 83.9Improved
raise retrieval threshold from 0.4 to 0.8 (ablation)LVAgent · LongVideoBenchaccuracy: 78.6 -> 80.0Improved

Later papers that compared with this method

4 later accepted papers report LVAgent as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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