VAMR: Multi-Question Agentic Reasoning for Efficient Long-Form Video Understanding

arXiv:2610.11171 · cs.CV, cs.AI · Submitted 2026-10-08 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-10-08

Updated: 2026-10-08

Terminology

• Accuracy — 44× in this paper · explained in 1 episode
• Ablation — 20× in this paper · explained in 1 episode
• Benchmark — 18× in this paper · explained in 2 episodes
• Alignment — 14× in this paper · explained in 1 episode
• Actor — 13× in this paper · explained in 3 episodes
• Reinforcement Learning — 8× in this paper · explained in 4 episodes
• Credit assignment — 4× in this paper · explained in 3 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Verification — 4× in this paper · explained in 2 episodes
• Ablation Studies — 3× in this paper · explained in 1 episode
• Agentic Reasoning — 3× in this paper · explained in 1 episode
• Trace — 3× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Video Agent for Multi-Question Reasoning — 2× in this paper
• AI Agents — 1× in this paper · explained in 2 episodes
• Agentic Framework — 1× in this paper · explained in 6 episodes
• Agentic Search — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• GRPO — 1× in this paper · explained in 6 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Multi-hop Reasoning — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Temporal Reasoning — 1× in this paper · explained in 2 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes

Sources

• Advancing Content Moderation: Evaluating Large Language Models for Detecting Sensitive Content Across Text, Images, and Videos
• Qwen3-VL Technical Report
• Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
• Group-in-Group Policy Optimization for LLM Agent Training
• LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning
• FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• LensWalk: Agentic Video Understanding by Planning How You See in Videos
• ToRL: Scaling Tool-Integrated RL
• Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA
• UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist
• Agent Lightning: Train ANY AI Agents with Reinforcement Learning
• TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning
• MR. Video: "MapReduce" is the Principle for Long Video Understanding
• VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority
• Proximal Policy Optimization Algorithms
• RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
• StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization
• VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
• Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Reward Design

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models