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

arXiv: https://arxiv.org/abs/2603.22918 · HTML: https://mlsanity.com/paper/2603.22918/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 36 of its 41 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 36)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [Long Context Transfer from Language to Vision](https://mlsanity.com/paper/2406.16852/) (2024)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [LVBench: An Extreme Long Video Understanding Benchmark](https://mlsanity.com/paper/2406.08035/) (2024)
- [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025)
- [ShareGPT4Video: Improving Video Understanding and Generation with Better Captions](https://mlsanity.com/paper/2406.04325/) (2024)
- [LongVILA: Scaling Long-Context Visual Language Models for Long Videos](https://mlsanity.com/paper/2408.10188/) (2024)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding](https://mlsanity.com/paper/2403.11481/) (2024)
- [Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions](https://mlsanity.com/paper/2111.10337/) (2021)
- [VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction](https://mlsanity.com/paper/2501.01957/) (2025)
- [Adaptive Keyframe Sampling for Long Video Understanding](https://mlsanity.com/paper/2502.21271/) (2025)
- [Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?](https://mlsanity.com/paper/2505.21374/) (2025)
- [Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory](https://mlsanity.com/paper/2508.09736/) (2025)
- [M-LLM Based Video Frame Selection for Efficient Video Understanding](https://mlsanity.com/paper/2502.19680/) (2025)
- [CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding](https://mlsanity.com/paper/2412.12075/) (2024)
- [Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning](https://mlsanity.com/paper/2506.13654/) (2025)
- [Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence](https://mlsanity.com/paper/2510.20579/) (2025)
- [FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting](https://mlsanity.com/paper/2509.24304/) (2025)
- [Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning](https://mlsanity.com/paper/2510.23473/) (2025)
- [Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding](https://mlsanity.com/paper/2508.20478/) (2025)

## Built on by (most cited first, 6 of 6)

- [MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning](https://mlsanity.com/paper/2605.14212/) (2026)
- [Routing Before Looking: Query-Adaptive Evidence Acquisition for Long-form Video Understanding](https://mlsanity.com/paper/2608.20805/) (2026)
- [Beneath the Scores: Rethinking Hallucination Evaluation for Video Understanding Models](https://mlsanity.com/paper/2609.28991/) (2026)
- [Agentic Video Understanding: A Survey](https://mlsanity.com/paper/2609.31713/) (2026)
- [Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution](https://mlsanity.com/paper/2609.37950/) (2026)
- [Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning](https://mlsanity.com/paper/2610.03099/) (2026)

## Abstract (arXiv)

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.