English(EN) System1-Arena: Which Decisions Can Be Left to System 1?

新的基准System1-Arena测试AI决策速度与准确性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-16 04:00

研究人员推出了System1-Arena，这是一个新的基准，旨在评估AI模型在做出离散决策方面的能力，区分“系统1”（快速、概率性）和“系统2”（基于推理）的方法。该基准包含92,000个问题，涵盖105个任务和138个闭环环境，测试模型在从文本分类到机器人和驾驶等复杂代理任务的各种能力。初步评估显示，大型系统1模型在准确性和概率校准方面可以媲美甚至超越快速的闭源LLM，而延迟却只有一小部分，尽管生成式推理模型在显著更高的成本下实现了最高的准确性。 AI

影响该基准通过提供一种标准化的方法来比较快速的概率模型和较慢的基于推理的模型，有可能加速更高效的AI决策系统的开发。

排序理由该集群包含一篇介绍AI模型评估新基准的研究论文。[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: 17 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇介绍AI模型评估新基准的研究论文。[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, other; 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) · Tianyu Chen, Xinyang Liu, Ruyi An, Zhendong Wang, Mingyuan Zhou · 2026-10-16 04:00

System1-Arena：哪些决策可以交给System 1？

arXiv:2610.21244v1 Announce Type: cross Abstract: Large language models (LLMs) often make discrete decisions, such as flagging phishing or escalating to a human. System-1 models, such as Jev and the OpenAI Decisions API, return probabilities over options in a single forward pass,…

本文如何被排名

报道来源 [1]

System1-Arena：哪些决策可以交给System 1？

相关实体

相关话题