EVA: Efficient Reinforcement Learning for End-to-End Video Agent

• URL: http://arxiv.org/abs/2603.22918v2
• Date: Thu, 26 Mar 2026 20:03:37 GMT
• Title: EVA: Efficient Reinforcement Learning for End-to-End Video Agent
• Abstract summary: We present EVA, an efficient Reinforcement Learning framework for End-to-End Video Agent.<n> EVA autonomously decides what to watch, when to watch, and how to watch, achieving query-driven and efficient video understanding.
• Score: 28.603844837930225
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video understanding with multimodal large language models (MLLMs) remains challenging due to the long token sequences of videos, which contain extensive temporal dependencies and redundant frames. Existing approaches typically treat MLLMs as passive recognizers, processing entire videos or uniformly sampled frames without adaptive reasoning. Recent agent-based methods introduce external tools, yet still depend on manually designed workflows and perception-first strategies, resulting in inefficiency on long videos. We present EVA, an Efficient Reinforcement Learning framework for End-to-End Video Agent, which enables planning-before-perception through iterative summary-plan-action-reflection reasoning. EVA autonomously decides what to watch, when to watch, and how to watch, achieving query-driven and efficient video understanding. To train such agents, we design a simple yet effective three-stage learning pipeline - comprising supervised fine-tuning (SFT), Kahneman-Tversky Optimization (KTO), and Group Relative Policy Optimization (GRPO) - that bridges supervised imitation and reinforcement learning. We further construct high-quality datasets for each stage, supporting stable and reproducible training. We evaluate EVA on six video understanding benchmarks, demonstrating its comprehensive capabilities. Compared with existing baselines, EVA achieves a substantial improvement of 6-12% over general MLLM baselines and a further 1-3% gain over prior adaptive agent methods.

Related papers

• Agentic Video Intelligence: A Flexible Framework for Advanced Video Exploration and Understanding [43.785571875867]
  We propose Agentic Video Intelligence (AVI), a flexible and training-free framework that can mirror human video comprehension through system-level design and optimization.<n>AVI introduces three key innovations: (1) a human-inspired three-phase reasoning process (Retrieve-Perceive-Review), (2) a structured video knowledge base organized through entity graphs, and (3) an open-source model ensemble combining reasoning LLMs with lightweight base CV models and VLM.
  arXiv  Detail & Related papers  (2025-11-18T12:43:15Z)
• Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models [78.32948112203228]
  Video understanding represents the most challenging frontier in computer vision.<n>Recent emergence of Video-Large Multitemporal Models has demonstrated remarkable capabilities in video understanding tasks.<n>Survey aims to provide researchers and practitioners with a unified framework for advancing Video-LMM capabilities.
  arXiv  Detail & Related papers  (2025-10-06T17:10:44Z)
• Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency [56.475612147721264]
  We propose a dual-reward formulation that supervises both semantic and temporal reasoning through discrete and continuous reward signals.<n>We evaluate our approach across eight representative video understanding tasks, including VideoQA, Temporal Video Grounding, and Grounded VideoQA.<n>Results underscore the importance of reward design and data selection in advancing reasoning-centric video understanding with MLLMs.
  arXiv  Detail & Related papers  (2025-06-02T17:28:26Z)
• ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding [71.654781631463]
  ReAgent-V is a novel agentic video understanding framework.<n>It integrates efficient frame selection with real-time reward generation during inference.<n>Extensive experiments on 12 datasets demonstrate significant gains in generalization and reasoning.
  arXiv  Detail & Related papers  (2025-06-02T04:23:21Z)
• ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning [68.76048244253582]
  We introduce ViaRL, the first framework to leverage rule-based reinforcement learning (RL) for optimizing frame selection in video understanding.<n>ViaRL utilizes the answer accuracy of a downstream model as a reward signal to train a frame selector through trial-and-error.<n>ViaRL consistently delivers superior temporal grounding performance and robust generalization across diverse video understanding tasks.
  arXiv  Detail & Related papers  (2025-05-21T12:29:40Z)
• Learning from Streaming Video with Orthogonal Gradients [62.51504086522027]
  We address the challenge of representation learning from a continuous stream of video as input, in a self-supervised manner.<n>This differs from the standard approaches to video learning where videos are chopped and shuffled during training in order to create a non-redundant batch.<n>We demonstrate the drop in performance when moving from shuffled to sequential learning on three tasks.
  arXiv  Detail & Related papers  (2025-04-02T17:59:57Z)
• ST-LLM: Large Language Models Are Effective Temporal Learners [58.79456373423189]
  Large Language Models (LLMs) have showcased impressive capabilities in text comprehension and generation. How to effectively encode and understand videos in video-based dialogue systems remains to be solved. We propose ST-LLM, an effective video-LLM baseline with spatial-temporal sequence modeling inside LLM.
  arXiv  Detail & Related papers  (2024-03-30T10:11:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.