# SVI-Bench：战略视频智能的动态微世界

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-29 08:00
- AIHOT 分数：68
- AIHOT 链接：https://aihot.virxact.com/items/cmpwv6g5q010osl793tbf7vk1
- 原文链接：https://arxiv.org/abs/2605.31529

## AI 摘要

SVI-Bench是一个用于评估战略视频智能(SVI)的大型基准测试，利用篮球、足球和冰球等团队运动作为动态微世界。其数据包含约35K小时广播视频、15M标注动作、15K小时专家评论、23K比赛报告及103K结构化统计记录。评估任务涵盖动态场景理解、因果推理、战略模拟和智能体综合四个递进层级。评估显示，模型在感知任务上能达到约73%准确率，但性能随认知层级提升而急剧下降；在需自主整合证据的智能体任务中，最强模型准确率仅为5%。

## 正文

True video intelligence demands more than recognizing what is visible: it requires reasoning about why events unfold, predicting what would change under different conditions, and deciding what to do next. We refer to this progression, from perception through causal reasoning and simulation to strategic planning, as Strategic Video Intelligence (SVI). No existing benchmark evaluates this capability stack: in-the-wild videos lack verifiable ground truth for causal and strategic questions, while synthetic environments sacrifice the complexity of real multi-agent systems. To bridge this gap, we introduce SVI-Bench, a large-scale benchmark that leverages team sports as a dynamic microworld, combining the complexity of real-world multi-agent interaction (10-22 agents making coordinated decisions under adversarial pressure) with the verifiability of explicit rules and definitive outcomes. SVI-Bench comprises approximately 35K hours of broadcast video, 15M annotated actions, 15K hours of expert commentary, 23K game reports, and 103K structured statistical records across basketball, soccer, and hockey, all constructed via a data engine that transforms raw game data into a dense, cross-referenced corpus. We organize evaluation into 9 tasks spanning a progressive four-pillar hierarchy: Dynamic Scene Understanding, Causal Reasoning, Strategic Simulation, and Agentic Synthesis. Evaluating strong multimodal and agentic baselines, we find a capability cliff: models perform competently on perceptual tasks, achieving approximately 73% on fine-grained action QA, but degrade sharply at each successive cognitive level. Agentic tasks prove hardest: the strongest model achieves only 5% accuracy when required to autonomously gather and integrate evidence across a corpus of 1.8M clips.