新的LOLPlay基准测试英雄联盟中的AI代理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-14 05:00

一个名为LOLPlay的新基准测试已被开发出来，用于评估《英雄联盟》中的实时视觉代理。该基准测试包含36个特定英雄的任务，涵盖资源管理、战斗、合作和目标争夺。在对三个模型的评估中，GPT-6 Astra在低和中等努力设置下实现了最高的25.0%任务成功率。然而，增加推理努力并没有提高任何模型的性能，并且对于GPT-6 Astra来说，这导致了更少的交互回合，表明推理深度与实时控制之间存在权衡。 AI

影响该基准测试有望推动AI代理在复杂、动态环境中实时决策和视觉推理能力的进步。

排序理由该集群描述了一个关于在复杂环境中评估AI代理的新基准测试和研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一个关于在复杂环境中评估AI代理的新基准测试和研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Zhaojian Yu · 2026-11-14 05:00

LOLPlay：英雄联盟实时视觉代理的基准测试

arXiv:2611.03685v2 Announce Type: replace Abstract: Visual agents need to coordinate reasoning and action while their environment evolves during inference. We introduce LOLPlay, a benchmark in native League of Legends with 36 champion-specific tasks spanning resource management, …

本文如何被排名

报道来源 [1]

LOLPlay：英雄联盟实时视觉代理的基准测试

相关实体

相关话题